arXiv subjects

Ramesh Karri

Publications and source records attributed to Ramesh Karri.

At least 73 records · Page 4Linked to original sources

arXiv2025

D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security

Large Language Models (LLMs) have been used in cybersecurity such as autonomous security analysis or penetration testing. Capture the Flag (CTF) challenges serve as benchmarks to assess automated task-planning abilities of LLM agents for cybersecurity. Early attempts to apply LLMs for solving CTF challenges used single-agent systems, where feedback was restricted to a single reasoning-action loop. This approach was inadequate for complex CTF tasks. Inspired by real-world CTF competitions, where teams of experts collaborate, we introduce the D-CIPHER LLM multi-agent framework for collaborative CTF solving. D-CIPHER integrates agents with distinct roles with dynamic feedback loops to enhance reasoning on complex tasks. It introduces the Planner-Executor agent system, consisting of a Planner agent for overall problem-solving along with multiple heterogeneous Executor agents for individual tasks, facilitating efficient allocation of responsibilities among the agents. Additionally, D-CIPHER incorporates an Auto-prompter agent to improve problem-solving by auto-generating a highly relevant initial prompt. We evaluate D-CIPHER on multiple CTF benchmarks and LLM models via comprehensive studies to highlight the impact of our enhancements. Additionally, we manually map the CTFs in NYU CTF Bench to MITRE ATT&CK techniques that apply for a comprehensive evaluation of D-CIPHER's offensive security capability. D-CIPHER achieves state-of-the-art performance on three benchmarks: 22.0% on NYU CTF Bench, 22.5% on Cybench, and 44.0% on HackTheBox, which is 2.5% to 8.5% better than previous work. D-CIPHER solves 65% more ATT&CK techniques compared to previous work, demonstrating stronger offensive capability.

cs.AI↗

arXiv2025

Veritas: Deterministic Verilog Code Synthesis from LLM-Generated Conjunctive Normal Form

Automated Verilog code synthesis poses significant challenges and typically demands expert oversight. Traditional high-level synthesis (HLS) methods often fail to scale for real-world designs. While large language models (LLMs) have enhanced scalability, they often introduce syntactical and logical errors requiring extensive post-generation verification. Here, we introduce a novel conjunctive normal form (CNF)-guided synthesis methodology. The idea is to have an LLM generate CNF clauses, a format widely used for formal verification and synthesis validation in hardware design, but here it is used to formally describe the desired circuit functionality. These CNF specifications are then deterministically converted into Verilog, ensuring correctness by construction. Our approach fine-tunes an open-source and lightweight LLM, namely the CPU-deployable LLama-3.2-3B-Instruct model (parameters < 4B), on a dataset of standard RTL components. Experimental results demonstrate that our approach reliably produces functionally correct Verilog code on the first attempt, compared to other lightweight open-source SoTA works such as Verigen (2B parameters) and RTLCoder (4-bit quantized with around 7B parameters). We will release our method and data in full post peer-review.

cs.AR↗

arXiv2025

LASHED: LLMs And Static Hardware Analysis for Early Detection of RTL Bugs

While static analysis is useful in detecting early-stage hardware security bugs, its efficacy is limited because it requires information to form checks and is often unable to explain the security impact of a detected vulnerability. Large Language Models can be useful in filling these gaps by identifying relevant assets, removing false violations flagged by static analysis tools, and explaining the reported violations. LASHED combines the two approaches (LLMs and Static Analysis) to overcome each other's limitations for hardware security bug detection. We investigate our approach on four open-source SoCs for five Common Weakness Enumerations (CWEs) and present strategies for improvement with better prompt engineering. We find that 87.5% of instances flagged by our recommended scheme are plausible CWEs. In-context learning and asking the model to 'think again' improves LASHED's precision.

cs.CR↗

arXiv2025

Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective

Recent Large Language Models (LLMs) such as OpenAI o3-mini and DeepSeek-R1 use enhanced reasoning through Chain-of-Thought (CoT). Their potential in hardware design, which relies on expert-driven iterative optimization, remains unexplored. This paper investigates whether reasoning LLMs can address challenges in High-Level Synthesis (HLS) design space exploration and optimization. During HLS, engineers manually define pragmas/directives to balance performance and resource constraints. We propose an LLM-based optimization agentic framework that automatically restructures code, inserts pragmas, and identifies optimal design points via feedback from HLs tools and access to integer-linear programming (ILP) solvers. Experiments compare reasoning models against conventional LLMs on benchmarks using success rate, efficiency, and design quality (area/latency) metrics, and provide the first-ever glimpse into the CoTs produced by a powerful open-source reasoning model like DeepSeek-R1.

cs.AI↗

arXiv2025

Masala-CHAI: A Large-Scale SPICE Netlist Dataset for Analog Circuits by Harnessing AI

Masala-CHAI is a fully automated framework leveraging large language models (LLMs) to generate Simulation Programs with Integrated Circuit Emphasis (SPICE) netlists. It addresses a long-standing challenge in circuit design automation: automating netlist generation for analog circuits. Automating this workflow could accelerate the creation of fine-tuned LLMs for analog circuit design and verification. In this work, we identify key challenges in automated netlist generation and evaluate multimodal capabilities of state-of-the-art LLMs, particularly GPT-4, in addressing them. We propose a three-step workflow to overcome existing limitations: labeling analog circuits, prompt tuning, and netlist verification. This approach enables end-to-end SPICE netlist generation from circuit schematic images, tackling the persistent challenge of accurate netlist generation. We utilize Masala-CHAI to collect a corpus of 7,500 schematics that span varying complexities in 10 textbooks and benchmark various open source and proprietary LLMs. Models fine-tuned on Masala-CHAI when used in LLM-agentic frameworks such as AnalogCoder achieve a notable 46% improvement in Pass@1 scores. We open-source our dataset and code for community-driven development.

cs.AR↗

arXiv2025

HiFi-CS: Towards Open Vocabulary Visual Grounding For Robotic Grasping Using Vision-Language Models

Robots interacting with humans through natural language can unlock numerous applications such as Referring Grasp Synthesis (RGS). Given a text query, RGS determines a stable grasp pose to manipulate the referred object in the robot's workspace. RGS comprises two steps: visual grounding and grasp pose estimation. Recent studies leverage powerful Vision-Language Models (VLMs) for visually grounding free-flowing natural language in real-world robotic execution. However, comparisons in complex, cluttered environments with multiple instances of the same object are lacking. This paper introduces HiFi-CS, featuring hierarchical application of Featurewise Linear Modulation (FiLM) to fuse image and text embeddings, enhancing visual grounding for complex attribute rich text queries encountered in robotic grasping. Visual grounding associates an object in 2D/3D space with natural language input and is studied in two scenarios: Closed and Open Vocabulary. HiFi-CS features a lightweight decoder combined with a frozen VLM and outperforms competitive baselines in closed vocabulary settings while being 100x smaller in size. Our model can effectively guide open-set object detectors like GroundedSAM to enhance open-vocabulary performance. We validate our approach through real-world RGS experiments using a 7-DOF robotic arm, achieving 90.33\% visual grounding accuracy in 15 tabletop scenes. Our codebase is provided here: https://github.com/vineet2104/hifics

cs.RO↗

arXiv2025

Automatically Improving LLM-based Verilog Generation using EDA Tool Feedback

Traditionally, digital hardware designs are written in the Verilog hardware description language (HDL) and debugged manually by engineers. This can be time-consuming and error-prone for complex designs. Large Language Models (LLMs) are emerging as a potential tool to help generate fully functioning HDL code, but most works have focused on generation in the single-shot capacity: i.e., run and evaluate, a process that does not leverage debugging and, as such, does not adequately reflect a realistic development process. In this work, we evaluate the ability of LLMs to leverage feedback from electronic design automation (EDA) tools to fix mistakes in their own generated Verilog. To accomplish this, we present an open-source, highly customizable framework, AutoChip, which combines conversational LLMs with the output from Verilog compilers and simulations to iteratively generate and repair Verilog. To determine the success of these LLMs we leverage the VerilogEval benchmark set. We evaluate four state-of-the-art conversational LLMs, focusing on readily accessible commercial models. EDA tool feedback proved to be consistently more effective than zero-shot prompting only with GPT-4o, the most computationally complex model we evaluated. In the best case, we observed a 5.8% increase in the number of successful designs with a 34.2% decrease in cost over the best zero-shot results. Mixing smaller models with this larger model at the end of the feedback iterations resulted in equally as much success as with GPT-4o using feedback, but incurred 41.9% lower cost (corresponding to an overall decrease in cost over zero-shot by 89.6%).

cs.AR↗

arXiv2025

NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security

Large Language Models (LLMs) are being deployed across various domains today. However, their capacity to solve Capture the Flag (CTF) challenges in cybersecurity has not been thoroughly evaluated. To address this, we develop a novel method to assess LLMs in solving CTF challenges by creating a scalable, open-source benchmark database specifically designed for these applications. This database includes metadata for LLM testing and adaptive learning, compiling a diverse range of CTF challenges from popular competitions. Utilizing the advanced function calling capabilities of LLMs, we build a fully automated system with an enhanced workflow and support for external tool calls. Our benchmark dataset and automated framework allow us to evaluate the performance of five LLMs, encompassing both black-box and open-source models. This work lays the foundation for future research into improving the efficiency of LLMs in interactive cybersecurity tasks and automated task planning. By providing a specialized benchmark, our project offers an ideal platform for developing, testing, and refining LLM-based approaches to vulnerability detection and resolution. Evaluating LLMs on these challenges and comparing with human performance yields insights into their potential for AI-driven cybersecurity solutions to perform real-world threat management. We make our benchmark dataset open source to public https://github.com/NYU-LLM-CTF/NYU_CTF_Bench along with our playground automated framework https://github.com/NYU-LLM-CTF/llm_ctf_automation.

cs.CR↗

arXiv2025

The Impact of Logic Locking on Confidentiality: An Automated Evaluation

Logic locking secures hardware designs in untrusted foundries by incorporating key-driven gates to obscure the original blueprint. While this method safeguards the integrated circuit from malicious alterations during fabrication, its influence on data confidentiality during runtime has been ignored. In this study, we employ path sensitization to formally examine the impact of logic locking on confidentiality. By applying three representative logic locking mechanisms on open-source cryptographic benchmarks, we utilize an automatic test pattern generation framework to evaluate the effect of locking on cryptographic encryption keys and sensitive data signals. Our analysis reveals that logic locking can inadvertently cause sensitive data leakage when incorrect logic locking keys are used. We show that a single malicious logic locking key can expose over 70% of an encryption key. If an adversary gains control over other inputs, the entire encryption key can be compromised. This research uncovers a significant security vulnerability in logic locking and emphasizes the need for comprehensive security assessments that extend beyond key-recovery attacks.

cs.CR↗

arXiv2025

Real-Time Multi-Modal Subcomponent-Level Measurements for Trustworthy System Monitoring and Malware Detection

With increasingly sophisticated cyber-adversaries able to access a wider repertoire of mechanisms to implant malware such as ransomware, CPU/GPU keyloggers, and stealthy kernel rootkits, there is an urgent need for techniques to detect and mitigate such attacks. While state of the art relies on digital and analog side channel measurements assuming trustworthiness of measurements obtained on the main processor, such an approach has limitations since processor-based side channel measurements are potentially untrustworthy. Sophisticated adversaries (especially in late stage cyber attacks when they have breached the computer and network security systems such as firewalls and antivirus and penetrated the computer's OS) can compromise user-space and kernel-space measurements. To address this key limitation of state of the art, we propose a "subcomponent-level" approach to collect side channel measurements so as to enable robust anomaly detection in a modern computer even when the main processor is compromised. Our proposed approach leverages the fact that modern computers are complex systems with multiple interacting subcomponents and measurements from subcomponents can be used to detect anomalies even when the main processor is no longer trustworthy. We develop mechanisms to obtain time series measurements of activity of several subcomponents and methodologies to process and fuse these measurements for anomaly detection. The subcomponents include network interface controller, GPU, CPU Hardware Performance Counters, CPU power, and keyboard. Our main hypothesis is that subcomponent measurements can enable detection of security threats without requiring a trustworthy main processor. By enabling real-time measurements from multiple subcomponents, the goal is to provide a deeper visibility into system operation, thereby yielding a powerful tool to track system operation and detect anomalies.

cs.CR↗

arXiv2024

RTL-Breaker: Assessing the Security of LLMs against Backdoor Attacks on HDL Code Generation

Large language models (LLMs) have demonstrated remarkable potential with code generation/completion tasks for hardware design. In fact, LLM-based hardware description language (HDL) code generation has enabled the industry to realize complex designs more quickly, reducing the time and effort required in the development cycle. However, the increased reliance on such automation introduces critical security risks. Notably, given that LLMs have to be trained on vast datasets of codes that are typically sourced from publicly available repositories (often without thorough validation), LLMs are susceptible to so-called data poisoning or backdoor attacks. Here, attackers inject malicious code for the training data, which can be carried over into the HDL code generated by LLMs. This threat vector can compromise the security and integrity of entire hardware systems. In this work, we propose RTL-Breaker, a novel backdoor attack framework on LLM-based HDL code generation. RTL-Breaker provides an in-depth analysis for essential aspects of this novel problem: 1) various trigger mechanisms versus their effectiveness for inserting malicious modifications, and 2) side-effects by backdoor attacks on code generation in general, i.e., impact on code quality. RTL-Breaker emphasizes the urgent need for more robust measures to safeguard against such attacks. Toward that end, we open-source our framework and all data.

cs.CR↗

arXiv2024

Survey of different Large Language Model Architectures: Trends, Benchmarks, and Challenges

Large Language Models (LLMs) represent a class of deep learning models adept at understanding natural language and generating coherent responses to various prompts or queries. These models far exceed the complexity of conventional neural networks, often encompassing dozens of neural network layers and containing billions to trillions of parameters. They are typically trained on vast datasets, utilizing architectures based on transformer blocks. Present-day LLMs are multi-functional, capable of performing a range of tasks from text generation and language translation to question answering, as well as code generation and analysis. An advanced subset of these models, known as Multimodal Large Language Models (MLLMs), extends LLM capabilities to process and interpret multiple data modalities, including images, audio, and video. This enhancement empowers MLLMs with capabilities like video editing, image comprehension, and captioning for visual content. This survey provides a comprehensive overview of the recent advancements in LLMs. We begin by tracing the evolution of LLMs and subsequently delve into the advent and nuances of MLLMs. We analyze emerging state-of-the-art MLLMs, exploring their technical features, strengths, and limitations. Additionally, we present a comparative analysis of these models and discuss their challenges, potential limitations, and prospects for future development.

cs.LG↗

arXiv2024

PrefixLLM: LLM-aided Prefix Circuit Design

Prefix circuits are fundamental components in digital adders, widely used in digital systems due to their efficiency in calculating carry signals. Synthesizing prefix circuits with minimized area and delay is crucial for enhancing the performance of modern computing systems. Recently, large language models (LLMs) have demonstrated a surprising ability to perform text generation tasks. We propose PrefixLLM, that leverages LLMs for prefix circuit synthesis. PrefixLLM transforms the prefix circuit synthesis task into a structured text generation problem, termed the Structured Prefix Circuit Representation (SPCR), and introduces an iterative framework to automatically and accurately generate valid SPCRs. We further present a design space exploration (DSE) framework that uses LLMs to iteratively search for area and delay optimized prefix circuits. Compared to state-of-the-art, PrefixLLM can reduce the area by 3.70% under the same delay constraint. This work highlights the use of LLMs in the synthesis of arithmetic circuits, which can be transformed into the structured text generation.

cs.AR↗

arXiv2024

OffRAMPS: An FPGA-based Intermediary for Analysis and Modification of Additive Manufacturing Control Systems

Cybersecurity threats in Additive Manufacturing (AM) are an increasing concern as AM adoption continues to grow. AM is now being used for parts in the aerospace, transportation, and medical domains. Threat vectors which allow for part compromise are particularly concerning, as any failure in these domains would have life-threatening consequences. A major challenge to investigation of AM part-compromises comes from the difficulty in evaluating and benchmarking both identified threat vectors as well as methods for detecting adversarial actions. In this work, we introduce a generalized platform for systematic analysis of attacks against and defenses for 3D printers. Our "OFFRAMPS" platform is based on the open-source 3D printer control board "RAMPS." OFFRAMPS allows analysis, recording, and modification of all control signals and I/O for a 3D printer. We show the efficacy of OFFRAMPS by presenting a series of case studies based on several Trojans, including ones identified in the literature, and show that OFFRAMPS can both emulate and detect these attacks, i.e., it can both change and detect arbitrary changes to the g-code print commands.

cs.CR↗

arXiv2024

Evaluating LLMs for Hardware Design and Test

Large Language Models (LLMs) have demonstrated capabilities for producing code in Hardware Description Languages (HDLs). However, most of the focus remains on their abilities to write functional code, not test code. The hardware design process consists of both design and test, and so eschewing validation and verification leaves considerable potential benefit unexplored, given that a design and test framework may allow for progress towards full automation of the digital design pipeline. In this work, we perform one of the first studies exploring how a LLM can both design and test hardware modules from provided specifications. Using a suite of 8 representative benchmarks, we examined the capabilities and limitations of the state-of-the-art conversational LLMs when producing Verilog for functional and verification purposes. We taped out the benchmarks on a Skywater 130nm shuttle and received the functional chip.

cs.AR↗

arXiv2024

Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Design

Large Language Models (LLMs) are effective in computer hardware synthesis via hardware description language (HDL) generation. However, LLM-assisted approaches for HDL generation struggle when handling complex tasks. We introduce a suite of hierarchical prompting techniques which facilitate efficient stepwise design methods, and develop a generalizable automation pipeline for the process. To evaluate these techniques, we present a benchmark set of hardware designs which have solutions with or without architectural hierarchy. Using these benchmarks, we compare various open-source and proprietary LLMs, including our own fine-tuned Code Llama-Verilog model. Our hierarchical methods automatically produce successful designs for complex hardware modules that standard flat prompting methods cannot achieve, allowing smaller open-source LLMs to compete with large proprietary models. Hierarchical prompting reduces HDL generation time and yields savings on LLM costs. Our experiments detail which LLMs are capable of which applications, and how to apply hierarchical methods in various modes. We explore case studies of generating complex cores using automatic scripted hierarchical prompts, including the first-ever LLM-designed processor with no human feedback. Tools for the Recurrent Optimization via Machine Editing (ROME) method can be found at https://github.com/ajn313/ROME-LLM

cs.AR↗

arXiv2024

Lightweight Countermeasures Against Static Power Side-Channel Attacks

This paper presents a novel defense strategy against static power side-channel attacks (PSCAs), a critical threat to cryptographic security. Our method is based on (1) carefully tuning high-Vth versus low-Vth cell selection during synthesis, accounting for both security and timing impact, and (2), at runtime, randomly switching the operation between these cells. This approach serves to significantly obscure static power patterns, which are at the heart of static PSCAs. Our experimental results on a commercial 28nm node show a drastic increase in the effort required for a successful attack, namely up to 96 times more traces. When compared to prior countermeasures, ours incurs little cost, making it a lightweight defense.

cs.CR↗

arXiv2024

SENTAUR: Security EnhaNced Trojan Assessment Using LLMs Against Undesirable Revisions

A globally distributed IC supply chain brings risks due to untrusted third parties. The risks span inadvertent use of hardware Trojan (HT), inserted Intellectual Property (3P-IP) or Electronic Design Automation (EDA) flows. HT can introduce stealthy HT behavior, prevent an IC work as intended, or leak sensitive data via side channels. To counter HTs, rapidly examining HT scenarios is a key requirement. While Trust-Hub benchmarks are a good starting point to assess defenses, they encompass a small subset of manually created HTs within the expanse of HT designs. Further, the HTs may disappear during synthesis. We propose a large language model (LLM) framework SENTAUR to generate a suite of legitimate HTs for a Register Transfer Level (RTL) design by learning its specifications, descriptions, and natural language descriptions of HT effects. Existing tools and benchmarks are limited; they need a learning period to construct an ML model to mimic the threat model and are difficult to reproduce. SENTAUR can swiftly produce HT instances by leveraging LLMs without any learning period and sanitizing the HTs facilitating their rapid assessment. Evaluation of SENTAUR involved generating effective, synthesizable, and practical HTs from TrustHub and elsewhere, investigating impacts of payloads/triggers at the RTL. While our evaluation focused on HT insertion, SENTAUR can generalize to automatically transform an RTL code to have defined functional modifications.

cs.CR↗