Searcharxiv⌕ Search

arXiv subjects

Prabuddha Chakraborty

Publications and source records attributed to Prabuddha Chakraborty.

At least 19 recordsLinked to original sources
arXiv2026

Projective corepresentations and cohomology of compact quantum groups

We study projective unitary (co)representations of compact quantum groups and the associated second cohomology theory. We introduce left/right/bi/strongly projective corepresentations and study them in details. In particular, we prove that given any compact quantum group $\q$, there are compact quantum groups $\tilde{\q_l}, \tilde{\q_r}, {\tilde \q}_{bi}, {\tilde \q}_{stp}$, each of which contains $\q$ as a Woronowicz subalgebra and every left/right/bi/strongly projective unitary corepresentation of $\q$ lifts to a linear corepresentation of these quantum groups respectively. We observe that the strongly projective corepresentations are associated with the second invariant ($S^1$-valued) cohomology $H^2_{uinv}(\cdot)$ of the quantum group. We define a suitable analogue of normalizer of a compact quantum group in a bigger compact quantum group and using this, associate a canonical discrete group $Γ_\q$ to a compact quantum group $\q$ which is an alternative generalization of the second group cohomology and we show by an example that $Γ_\q$ in general may be different from $H^2_{uinv}(\q,S^1) $. We also illustrate with examples that $Γ_{\q}$ is more suitable than $H^2_{uinv}(., S^1)$ for labeling topological phases under quantum group symmetry.

math.QA↗
arXiv2026

(A)iSpy: Parasitic Trojans for Machine Learning Infrastructure

Modern machine learning (ML) pipelines depend heavily on third party libraries for graph compilation and hardware acceleration. While current practices audit data and model artifacts or rely on file integrity checks, the execution environment remains implicitly trusted. This blind spot enables active threats where a malicious runtime module interacts directly with live training and inference dynamics: exploiting this interaction allows the Trojan to support complex objectives that are challenging for static code or binary modifications, achieving manipulations impossible for standard data and model level attacks. We expose this vulnerability by presenting AiSPY, a parasitic infrastructure Trojan that subverts MLsystems through an active observe and execute paradigm. Operating within the computation graph, AiSPY monitors transient tensor states to perform targeted, stealthy manipulations with negligible overhead. To violate confidentiality, the Trojan identifies all critical training hyperparameters and covertly exfiltrates them via model weights or output logits. To break integrity, it acts as a gradient amplifier: by observing steganographic triggers, it transforms other- wise weak data poisoning into effective backdoor attacks, increasing success rates from near zero to 100%. We further demonstrate broad extensibility across the machine learning lifecycle by validating auxiliary attacks in the appendix, including subpopulation label flipping, availability disruptions, and inference stage manipulations. Importantly, the evaluated malware scanners do not flag AiSPY because current public rule sets lack coverage for ML runtime Trojans, while the associated poisoned inputs and resulting compromised models bypass state-of-the-art inspection tools. We demonstrate the practicality of this threat with an implementation in the ONNX Runtime training and inference engines.

cs.CR↗
arXiv2026

DISARM: Target Electronic Device Informed Mitigation of Software Runtime Side-Channel Vulnerabilities

Program runtime or timing attacks exploit variations in a program's execution times to extract sensitive information from the program (e.g. encryption keys, sensitive variable data, intellectual property). State-of-the-art solutions to runtime side-channel attacks attempt to balance the execution time of the sensitive code for different control flow paths to eliminate the timing leakage. However, during the mitigation process, most techniques do not consider the underlying hardware or device on which the target program is supposed to run on. This can lead to over-fixing (unnecessary extra operations), under-fixing (not solving the imbalance properly), and even failures. We propose DISARM, a joint hardware-software methodology (unlike any existing solution) for mitigating runtime side-channel vulnerabilities that utilizes timing values from real embedded devices to generate targeted software fixes. We implement DISARM to support C, C++, and Java source codes and validate it across 22 standard benchmarks. DISARM outperforms state-of-the-art solutions such as PENDULUM and DifFuzzAR in terms of execution time overhead, code size overhead, and correctness on five different embedded or edge devices.

cs.CR↗
arXiv2026

HARP: Measuring Harm Amplification in Multi-Agent LLM Systems

Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretability, but creates a propagation risk: a bounded perturbation to one component can be reused by other agents and amplified into system-level harm. We introduce HARP (Harm Amplification through Role Perturbation), a trace-first methodology for studying local-to-global harm amplification in multi-agent LLM systems. HARP compares paired clean and perturbed executions and records specialist outputs, tool calls, memory reads/writes, guard events, oracle logs, latency, token cost, and decisions. We define local harm as deviation from targeted agents or corrupted channels, global harm as deviation over the full trace, and harm amplification as (H_global/H_local). This complements attack success rate with a measure of how strongly orchestration spreads harm beyond the attack point. We instantiate HARP in a finance-oriented seven-agent system with a deterministic decision gate and configurable attack harness for specialist compromise, collusion, shared-context corruption, and temporal or memory-persistent attacks. Across five defenses, prompt-only defenses preserve benign utility but leave high success and stealth; pre-tool and step-level guards reduce some failures with utility or latency costs; and IntegrityGuard, a trace-consistency defense, achieves the lowest attack success and global harm but introduces utility/cost trade-offs. Results show that single-specialist compromise produces the strongest amplification, shared-context corruption yields the highest attack success, and temporal persistence produces the largest malicious impact. HARP argues that secure multi-agent evaluation must measure not only bypass, but propagation.

cs.CR↗
arXiv2026

DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples

Numerous techniques have been proposed for generating adversarial examples in white-box settings under strict Lp-norm constraints. However, such norm-bounded examples often fail to align well with human perception, and only a few methods specifically explore perceptually aligned adversarial examples. Moreover, it remains unclear whether insights from Lp-constrained attacks can be effectively leveraged to improve perceptual efficacy. In this paper, we introduce DASH, a fully differentiable meta-attack framework that generates effective and perceptually aligned adversarial examples by strategically composing existing Lp-based attack methods. DASH operates in a multi-stage fashion: at each stage, it aggregates candidate adversarial examples from multiple base attacks using learned, adaptive weights and propagates the result to the next stage. A novel meta-loss function guides this process by jointly minimizing misclassification loss and perceptual distortion, enabling the framework to dynamically modulate the contribution of each base attack throughout the stages. We evaluate DASH on adversarially trained models across CIFAR-10, CIFAR-100, and ImageNet. Despite relying solely on Lp-constrained based methods, DASH significantly outperforms state-of-the-art perceptual attacks such as AdvAD, achieving higher attack success rates (e.g., 20.63% improvement) and superior visual quality, as measured by SSIM, LPIPS, and FID (improvements $\approx$ of 11, 0.015, and 5.7, respectively). Furthermore, DASH generalizes well to unseen defenses, making it a practical and strong baseline for evaluating robustness without requiring handcrafted adaptive attacks for each new defense.

cs.CV↗
arXiv2026

LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models

Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial prompting. Existing automated methods are increasingly effective but each commits to a single attack family (e.g., one refinement loop, one tree search, one mutation space, or one strategy library) and no single family dominates: the best-performing method shifts across target models and harm categories, suggesting complementary strengths that per-prompt composition could exploit. We introduce LASH (LLM Adaptive Semantic Hybridization), a black-box framework that treats outputs from multiple base attacks as reusable seed prompts and adaptively composes them for each target request. Given a seed pool, LASH searches over seed subsets and softmax-normalized mixture weights; a composition module synthesizes a single candidate prompt, and a derivative-free genetic optimizer updates the weights using black-box target feedback and a two-stage fitness function combining keyword-based refusal detection with LLM-judge scoring. On JailbreakBench, which contains 100 harmful prompts across 10 categories, we evaluate LASH on six common target models. LASH achieves an average attack success rate of 84.5% under keyword-based evaluation and 74.5% under two-stage evaluation, where responses are first filtered for refusals and then scored by an LLM judge for whether they substantively fulfill the original harmful request. LASH outperforms five state-of-the-art baselines on both metrics with only 30 mean target queries. LASH also remains competitive under three defense mechanisms and induces more success-like internal representations. These results suggest that adaptive composition across heterogeneous jailbreak strategies is a promising direction for black-box red-teaming.

cs.CL↗
arXiv2025

How a Bit Becomes a Story: Semantic Steering via Differentiable Fault Injection

Hard-to-detect hardware bit flips, from either malicious circuitry or bugs, have already been shown to make transformers vulnerable in non-generative tasks. This work, for the first time, investigates how low-level, bitwise perturbations (fault injection) to the weights of a large language model (LLM) used for image captioning can influence the semantic meaning of its generated descriptions while preserving grammatical structure. While prior fault analysis methods have shown that flipping a few bits can crash classifiers or degrade accuracy, these approaches overlook the semantic and linguistic dimensions of generative systems. In image captioning models, a single flipped bit might subtly alter how visual features map to words, shifting the entire narrative an AI tells about the world. We hypothesize that such semantic drifts are not random but differentiably estimable. That is, the model's own gradients can predict which bits, if perturbed, will most strongly influence meaning while leaving syntax and fluency intact. We design a differentiable fault analysis framework, BLADE (Bit-level Fault Analysis via Differentiable Estimation), that uses gradient-based sensitivity estimation to locate semantically critical bits and then refines their selection through a caption-level semantic-fluency objective. Our goal is not merely to corrupt captions, but to understand how meaning itself is encoded, distributed, and alterable at the bit level, revealing that even imperceptible low-level changes can steer the high-level semantics of generative vision-language models. It also opens pathways for robustness testing, adversarial defense, and explainable AI, by exposing how structured bit-level faults can reshape a model's semantic output.

cs.LG↗
arXiv2025

POLARIS: Explainable Artificial Intelligence for Mitigating Power Side-Channel Leakage

Microelectronic systems are widely used in many sensitive applications (e.g., manufacturing, energy, defense). These systems increasingly handle sensitive data (e.g., encryption key) and are vulnerable to diverse threats, such as, power side-channel attacks, which infer sensitive data through dynamic power profile. In this paper, we present a novel framework, POLARIS for mitigating power side channel leakage using an Explainable Artificial Intelligence (XAI) guided masking approach. POLARIS uses an unsupervised process to automatically build a tailored training dataset and utilize it to train a masking model.The POLARIS framework outperforms state-of-the-art mitigation solutions (e.g., VALIANT) in terms of leakage reduction, execution time, and overhead across large designs.

cs.CR↗
arXiv2025

SALTY: Explainable Artificial Intelligence Guided Structural Analysis for Hardware Trojan Detection

Hardware Trojans are malicious modifications in digital designs that can be inserted by untrusted supply chain entities. Hardware Trojans can give rise to diverse attack vectors such as information leakage (e.g. MOLES Trojan) and denial-of-service (rarely triggered bit flip). Such an attack in critical systems (e.g. healthcare and aviation) can endanger human lives and lead to catastrophic financial loss. Several techniques have been developed to detect such malicious modifications in digital designs, particularly for designs sourced from third-party intellectual property (IP) vendors. However, most techniques have scalability concerns (due to unsound assumptions during evaluation) and lead to large number of false positive detections (false alerts). Our framework (SALTY) mitigates these concerns through the use of a novel Graph Neural Network architecture (using Jumping-Knowledge mechanism) for generating initial predictions and an Explainable Artificial Intelligence (XAI) approach for fine tuning the outcomes (post-processing). Experiments show 98% True Positive Rate (TPR) and True Negative Rate (TNR), significantly outperforming state-of-the-art techniques across a large set of standard benchmarks.

cs.CR↗
arXiv2024

ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applications

Artificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analysis on same data) and are deployed on resource-constrained edge devices requiring the AI models to be efficient across different metrics such as power, frame rate, and size. For these specific use-cases, in this work, we propose a new paradigm of neural network architecture (ILASH) that leverages a layer sharing concept for minimizing power utilization, increasing frame rate, and reducing model size. Additionally, we propose a novel neural network architecture search framework (ILASH-NAS) for efficient construction of these neural network models for a given set of tasks and device constraints. The proposed NAS framework utilizes a data-driven intelligent approach to make the search efficient in terms of energy, time, and CO2 emission. We perform extensive evaluations of the proposed layer shared architecture paradigm (ILASH) and the ILASH-NAS framework using four open-source datasets (UTKFace, MTFL, CelebA, and Taskonomy). We compare ILASH-NAS with AutoKeras and observe significant improvement in terms of both the generated model performance and neural search efficiency with up to 16x less energy utilization, CO2 emission, and training/search time.

cs.LG↗
arXiv2024

X-DFS: Explainable Artificial Intelligence Guided Design-for-Security Solution Space Exploration

Design and manufacturing of integrated circuits predominantly use a globally distributed semiconductor supply chain involving diverse entities. The modern semiconductor supply chain has been designed to boost production efficiency, but is filled with major security concerns such as malicious modifications (hardware Trojans), reverse engineering (RE), and cloning. While being deployed, digital systems are also subject to a plethora of threats such as power, timing, and electromagnetic (EM) side channel attacks. Many Design-for-Security (DFS) solutions have been proposed to deal with these vulnerabilities, and such solutions (DFS) relays on strategic modifications (e.g., logic locking, side channel resilient masking, and dummy logic insertion) of the digital designs for ensuring a higher level of security. However, most of these DFS strategies lack robust formalism, are often not human-understandable, and require an extensive amount of human expert effort during their development/use. All of these factors make it difficult to keep up with the ever growing number of microelectronic vulnerabilities. In this work, we propose X-DFS, an explainable Artificial Intelligence (AI) guided DFS solution-space exploration approach that can dramatically cut down the mitigation strategy development/use time while enriching our understanding of the vulnerability by providing human-understandable decision rationale. We implement X-DFS and comprehensively evaluate it for reverse engineering threats (SAIL, SWEEP, and OMLA) and formalize a generalized mechanism for applying X-DFS to defend against other threats such as hardware Trojans, fault attacks, and side channel attacks for seamless future extensions.

cs.CR↗
arXiv2024

LeMo-NADe: Multi-Parameter Neural Architecture Discovery with LLMs

Building efficient neural network architectures can be a time-consuming task requiring extensive expert knowledge. This task becomes particularly challenging for edge devices because one has to consider parameters such as power consumption during inferencing, model size, inferencing speed, and CO2 emissions. In this article, we introduce a novel framework designed to automatically discover new neural network architectures based on user-defined parameters, an expert system, and an LLM trained on a large amount of open-domain knowledge. The introduced framework (LeMo-NADe) is tailored to be used by non-AI experts, does not require a predetermined neural architecture search space, and considers a large set of edge device-specific parameters. We implement and validate this proposed neural architecture discovery framework using CIFAR-10, CIFAR-100, and ImageNet16-120 datasets while using GPT-4 Turbo and Gemini as the LLM component. We observe that the proposed framework can rapidly (within hours) discover intricate neural network models that perform extremely well across a diverse set of application settings defined by the user.

cs.LG↗
arXiv2022

Automatic Hardware Trojan Insertion using Machine Learning

Due to the current horizontal business model that promotes increasing reliance on untrusted third-party Intellectual Properties (IPs), CAD tools, and design facilities, hardware Trojan attacks have become a serious threat to the semiconductor industry. Development of effective countermeasures against hardware Trojan attacks requires: (1) fast and reliable exploration of the viable Trojan attack space for a given design and (2) a suite of high-quality Trojan-inserted benchmarks that meet specific standards. The latter has become essential for the development and evaluation of design/verification solutions to achieve quantifiable assurance against Trojan attacks. While existing static benchmarks provide a baseline for comparing different countermeasures, they only enumerate a limited number of handcrafted Trojans from the complete Trojan design space. To accomplish these dual objectives, in this paper, we present MIMIC, a novel AI-guided framework for automatic Trojan insertion, which can create a large population of valid Trojans for a given design by mimicking the properties of a small set of known Trojans. While there exist tools to automatically insert Trojan instances using fixed Trojan templates, they cannot analyze known Trojan attacks for creating new instances that accurately capture the threat model. MIMIC works in two major steps: (1) it analyzes structural and functional features of existing Trojan populations in a multi-dimensional space to train machine learning models and generate a large number of "virtual Trojans" of the given design, (2) next, it binds them into the design by matching their functional/structural properties with suitable nets of the internal logic structure. We have developed a complete tool flow for MIMIC, extensively evaluated the framework by exploring several use-cases, and quantified its effectiveness to demonstrate highly promising results.

cs.CR↗
arXiv2021

Software Variants for Hardware Trojan Detection and Resilience in COTS Processors

The commercial off-the-shelf (COTS) component based ecosystem provides an attractive system design paradigm due to the drastic reduction in development time and cost compared to custom solutions. However, it brings in a growing concern of trustworthiness arising from the possibility of embedded malicious logic, or hardware Trojans in COTS components. Existing trust-verification approaches are typically not applicable to COTS hardware due to the absence of golden models and the lack of observability of internal signals. In this work, we propose a novel approach for runtime Trojan detection and resilience in untrusted COTS processors through judicious modifications in software. The proposed approach does not rely on any hardware redundancy or architectural modification and hence seamlessly integrates with the COTS-based system design process. Trojan resilience is achieved through the execution of multiple functionally equivalent software variants. We have developed and implemented a solution for compiler-based automatic generation of program variants, metric-guided selection of variants, and their integration in a single executable. To evaluate the proposed approach, we first analyzed the effectiveness of program variants in avoiding the activation of a random pool of Trojans. By implementing several Trojans in an OpenRISC 1000 processor, we analyzed the detectability and resilience during Trojan activation in both single and multiple variants. We also present delay and code size overhead for the automatically generated variants for several programs and discuss future research directions to reduce the overhead.

cs.CR↗
arXiv2021

Third-Party Hardware IP Assurance against Trojans through Supervised Learning and Post-processing

System-on-chip (SoC) developers increasingly rely on pre-verified hardware intellectual property (IP) blocks acquired from untrusted third-party vendors. These IPs might contain hidden malicious functionalities or hardware Trojans to compromise the security of the fabricated SoCs. Recently, supervised machine learning (ML) techniques have shown promising capability in identifying nets of potential Trojans in third party IPs (3PIPs). However, they bring several major challenges. First, they do not guide us to an optimal choice of features that reliably covers diverse classes of Trojans. Second, they require multiple Trojan-free/trusted designs to insert known Trojans and generate a trained model. Even if a set of trusted designs are available for training, the suspect IP could be inherently very different from the set of trusted designs, which may negatively impact the verification outcome. Third, these techniques only identify a set of suspect Trojan nets that require manual intervention to understand the potential threat. In this paper, we present VIPR, a systematic machine learning (ML) based trust verification solution for 3PIPs that eliminates the need for trusted designs for training. We present a comprehensive framework, associated algorithms, and a tool flow for obtaining an optimal set of features, training a targeted machine learning model, detecting suspect nets, and identifying Trojan circuitry from the suspect nets. We evaluate the framework on several Trust-Hub Trojan benchmarks and provide a comparative analysis of detection performance across different trained models, selection of features, and post-processing techniques. The proposed post-processing algorithms reduce false positives by up to 92.85%.

cs.CR↗
arXiv2021

Neural Storage: A New Paradigm of Elastic Memory

Storage and retrieval of data in a computer memory plays a major role in system performance. Traditionally, computer memory organization is static - i.e., they do not change based on the application-specific characteristics in memory access behaviour during system operation. Specifically, the association of a data block with a search pattern (or cues) as well as the granularity of a stored data do not evolve. Such a static nature of computer memory, we observe, not only limits the amount of data we can store in a given physical storage, but it also misses the opportunity for dramatic performance improvement in various applications. On the contrary, human memory is characterized by seemingly infinite plasticity in storing and retrieving data - as well as dynamically creating/updating the associations between data and corresponding cues. In this paper, we introduce Neural Storage (NS), a brain-inspired learning memory paradigm that organizes the memory as a flexible neural memory network. In NS, the network structure, strength of associations, and granularity of the data adjust continuously during system operation, providing unprecedented plasticity and performance benefits. We present the associated storage/retrieval/retention algorithms in NS, which integrate a formalized learning process. Using a full-blown operational model, we demonstrate that NS achieves an order of magnitude improvement in memory access performance for two representative applications when compared to traditional content-based memory.

cs.AI↗
arXiv2020

Leveraging Domain Knowledge using Machine Learning for Image Compression in Internet-of-Things

The emergent ecosystems of intelligent edge devices in diverse Internet of Things (IoT) applications, from automatic surveillance to precision agriculture, increasingly rely on recording and processing variety of image data. Due to resource constraints, e.g., energy and communication bandwidth requirements, these applications require compressing the recorded images before transmission. For these applications, image compression commonly requires: (1) maintaining features for coarse-grain pattern recognition instead of the high-level details for human perception due to machine-to-machine communications; (2) high compression ratio that leads to improved energy and transmission efficiency; (3) large dynamic range of compression and an easy trade-off between compression factor and quality of reconstruction to accommodate a wide diversity of IoT applications as well as their time-varying energy/performance needs. To address these requirements, we propose, MAGIC, a novel machine learning (ML) guided image compression framework that judiciously sacrifices visual quality to achieve much higher compression when compared to traditional techniques, while maintaining accuracy for coarse-grained vision tasks. The central idea is to capture application-specific domain knowledge and efficiently utilize it in achieving high compression. We demonstrate that the MAGIC framework is configurable across a wide range of compression/quality and is capable of compressing beyond the standard quality factor limits of both JPEG 2000 and WebP. We perform experiments on representative IoT applications using two vision datasets and show up to 42.65x compression at similar accuracy with respect to the source. We highlight low variance in compression rate across images using our technique as compared to JPEG 2000 and WebP.

cs.CV↗
arXiv2020

P2C2: Peer-to-Peer Car Charging

With the rising concerns of fossil fuel depletion and the impact of Internal Combustion Engine(ICE) vehicles on our climate, the transportation industry is observing a rapid proliferation of electric vehicles (EVs). However, long-distance travel withEV is not possible yet without making multiple halt at EV charging stations. Many remote regions do not have charging stations, and even if they are present, it can take several hours to recharge the battery. Conversely, ICE vehicle fueling stations are much more prevalent, and re-fueling takes a couple of minutes. These facts have deterred many from moving to EVs. Existing solutions to these problems, such as building more charging stations, increasing battery capacity, and road-charging have not been proven efficient so far. In this paper, we propose Peer-to-Peer Car Charging (P2C2), a highly scalable novel technique for charging EVs on the go with minimal cost overhead. We allow EVs to share charge among each others based on the instructions from a cloud-based control system. The control system assigns and guides EVs for charge sharing. We also introduce mobile Charging Stations (MoCS), which are high battery capacity vehicles that are used to replenish the overall charge in the vehicle networks. We have implemented P2C2 and integrated it with the traffic simulator, SUMO. We observe promising results with up to 65% reduction in the number of EV halts with up to 24.4% reduction in required battery capacity without any extra halts.

physics.soc-ph↗