arXiv subjects

Mahmood Sharif

Publications and source records attributed to Mahmood Sharif.

At least 19 recordsLinked to original sources

arXiv2026

TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization

Discrete text-trigger optimization -- searching for text sequences that, when ingested by a model, steer it toward a specified objective -- underpins model red-teaming (e.g., LLM jailbreaks), as well as auditing and interpretability. However, the current state of discrete optimizers hinders their adoption and progress. First, existing optimizers, when open-sourced at all, are scattered across research codebases tied to specific models, objectives, and problem domains. Second, optimizer variants proliferate, each requiring engineering overhead to use or extend, and remaining hard to compare head-to-head. Together, these raise the bar for adopting optimizers in existing or new domains, and for advancing them via new strategies. We address these gaps with TROPT, the first open-source framework that unifies discrete optimizers' execution and standardizes their development under a single interface. TROPT makes it easy to customize end-to-end optimization recipes by swapping any component -- models, objectives, and optimizers -- extending its reach across domains and new applications. TROPT currently ships with 30+ optimization recipes -- covering applications such as jailbreaking and probing model internals -- built from 15+ optimizers (spanning white-box to black-box access) and 15+ losses, from foundational to state-of-the-art methods. Demonstrating its utility, we leverage TROPT in several studies: (i) controlled, large-scale experiments comparing and enhancing optimization strategies for LLM jailbreaks, revealing potent-yet-underadopted techniques; and (ii) porting optimizers from one domain (e.g., LLM jailbreak) to new domains (e.g., corpus-poisoning embedding model). In all, TROPT significantly lowers the barrier to adopting and advancing discrete text optimization.

cs.LG↗

arXiv2025

Exploring Membership Inference Vulnerabilities in Clinical Large Language Models

As large language models (LLMs) become progressively more embedded in clinical decision-support, documentation, and patient-information systems, ensuring their privacy and trustworthiness has emerged as an imperative challenge for the healthcare sector. Fine-tuning LLMs on sensitive electronic health record (EHR) data improves domain alignment but also raises the risk of exposing patient information through model behaviors. In this work-in-progress, we present an exploratory empirical study on membership inference vulnerabilities in clinical LLMs, focusing on whether adversaries can infer if specific patient records were used during model training. Using a state-of-the-art clinical question-answering model, Llemr, we evaluate both canonical loss-based attacks and a domain-motivated paraphrasing-based perturbation strategy that more realistically reflects clinical adversarial conditions. Our preliminary findings reveal limited but measurable membership leakage, suggesting that current clinical LLMs provide partial resistance yet remain susceptible to subtle privacy risks that could undermine trust in clinical AI adoption. These results motivate continued development of context-aware, domain-specific privacy evaluations and defenses such as differential privacy fine-tuning and paraphrase-aware training, to strengthen the security and trustworthiness of healthcare AI systems.

cs.CR↗

arXiv2025

NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models

With the rapid adoption of diffusion models for visual content generation, proving authorship and protecting copyright have become critical. This challenge is particularly important when model owners keep their models private and may be unwilling or unable to handle authorship issues, making third-party verification essential. A natural solution is to embed watermarks for later verification. However, existing methods require access to model weights and rely on computationally heavy procedures, rendering them impractical and non-scalable. To address these challenges, we propose NoisePrints, a lightweight watermarking scheme that utilizes the random seed used to initialize the diffusion process as a proof of authorship without modifying the generation process. Our key observation is that the initial noise derived from a seed is highly correlated with the generated visual content. By incorporating a hash function into the noise sampling process, we further ensure that recovering a valid seed from the content is infeasible. We also show that sampling an alternative seed that passes verification is infeasible, and demonstrate the robustness of our method under various manipulations. Finally, we show how to use cryptographic zero-knowledge proofs to prove ownership without revealing the seed. By keeping the seed secret, we increase the difficulty of watermark removal. In our experiments, we validate NoisePrints on multiple state-of-the-art diffusion models for images and videos, demonstrating efficient verification using only the seed and output, without requiring access to model weights.

cs.CV↗

arXiv2025

Sy-FAR: Symmetry-based Fair Adversarial Robustness

Security-critical machine-learning (ML) systems, such as face-recognition systems, are susceptible to adversarial examples, including real-world physically realizable attacks. Various means to boost ML's adversarial robustness have been proposed; however, they typically induce unfair robustness: It is often easier to attack from certain classes or groups than from others. Several techniques have been developed to improve adversarial robustness while seeking perfect fairness between classes. Yet, prior work has focused on settings where security and fairness are less critical. Our insight is that achieving perfect parity in realistic fairness-critical tasks, such as face recognition, is often infeasible -- some classes may be highly similar, leading to more misclassifications between them. Instead, we suggest that seeking symmetry -- i.e., attacks from class $i$ to $j$ would be as successful as from $j$ to $i$ -- is more tractable. Intuitively, symmetry is a desirable because class resemblance is a symmetric relation in most domains. Additionally, as we prove theoretically, symmetry between individuals induces symmetry between any set of sub-groups, in contrast to other fairness notions where group-fairness is often elusive. We develop Sy-FAR, a technique to encourage symmetry while also optimizing adversarial robustness and extensively evaluate it using five datasets, with three model architectures, including against targeted and untargeted realistic attacks. The results show Sy-FAR significantly improves fair adversarial robustness compared to state-of-the-art methods. Moreover, we find that Sy-FAR is faster and more consistent across runs. Notably, Sy-FAR also ameliorates another type of unfairness we discover in this work -- target classes that adversarial examples are likely to be classified into become significantly less vulnerable after inducing symmetry.

cs.LG↗

arXiv2025

Reconstructing Template-Memorized Images from Natural Prompts

Recent advances in generative models, such as diffusion models, have raised concerns related to privacy, copyright infringement, and data stewardship. To better understand and control these risks, prior work has introduced techniques and attacks that reconstruct images, or parts of images, from training data. While these results demonstrate that training data can be recovered, existing methods often rely on high computational resources, partial access to the training set, or carefully engineered prompts. In this work, we present a new attack that requires low resources, assumes little to no access to the training data, and identifies seemingly benign prompts that can lead to potentially risky image reconstruction. We further show that such reconstructions may occur unintentionally, even for users without specialized knowledge. For example, we observe that for one existing model, the prompt ``blue Unisex T-Shirt'' generates the face of a real individual. Moreover, by combining the identified vulnerabilities with real-world prompt data, we discover prompts that reproduce memorized visual elements. Our approach builds on insights from prior work and leverages domain knowledge to expose a fundamental vulnerability arising from the use of scraped e-commerce data, where templated layouts and images are closely tied to pattern-like textual prompts. The code for our attack is publicly available at https://github.com/TheSolY/lr-tmi.

cs.LG↗

arXiv2025

Universal Jailbreak Suffixes Are Strong Attention Hijackers

We study suffix-based jailbreaks$\unicode{x2013}$a powerful family of attacks against large language models (LLMs) that optimize adversarial suffixes to circumvent safety alignment. Focusing on the widely used foundational GCG attack, we observe that suffixes vary in efficacy: some are markedly more universal$\unicode{x2013}$generalizing to many unseen harmful instructions$\unicode{x2013}$than others. We first show that a shallow, critical mechanism drives GCG's effectiveness. This mechanism builds on the information flow from the adversarial suffix to the final chat template tokens before generation. Quantifying the dominance of this mechanism during generation, we find GCG irregularly and aggressively hijacks the contextualization process. Crucially, we tie hijacking to the universality phenomenon, with more universal suffixes being stronger hijackers. Subsequently, we show that these insights have practical implications: GCG's universality can be efficiently enhanced (up to $\times$5 in some cases) at no additional computational cost, and can also be surgically mitigated, at least halving the attack's success with minimal utility loss. We release our code and data at http://github.com/matanbt/interp-jailbreak.

cs.CR↗

arXiv2025

CaFA: Cost-aware, Feasible Attacks With Database Constraints Against Neural Tabular Classifiers

This work presents CaFA, a system for Cost-aware Feasible Attacks for assessing the robustness of neural tabular classifiers against adversarial examples realizable in the problem space, while minimizing adversaries' effort. To this end, CaFA leverages TabPGD$-$an algorithm we set forth to generate adversarial perturbations suitable for tabular data$-$ and incorporates integrity constraints automatically mined by state-of-the-art database methods. After producing adversarial examples in the feature space via TabPGD, CaFA projects them on the mined constraints, leading, in turn, to better attack realizability. We tested CaFA with three datasets and two architectures and found, among others, that the constraints we use are of higher quality (measured via soundness and completeness) than ones employed in prior work. Moreover, CaFA achieves higher feasible success rates$-$i.e., it generates adversarial examples that are often misclassified while satisfying constraints$-$than prior attacks while simultaneously perturbing few features with lower magnitudes, thus saving effort and improving inconspicuousness. We open-source CaFA, hoping it will serve as a generic system enabling machine-learning engineers to assess their models' robustness against realizable attacks, thus advancing deployed models' trustworthiness.

cs.CR↗

arXiv2024

GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search

Dense embedding-based text retrieval$\unicode{x2013}$retrieval of relevant passages from corpora via deep learning encodings$\unicode{x2013}$has emerged as a powerful method attaining state-of-the-art search results and popularizing Retrieval Augmented Generation (RAG). Still, like other search methods, embedding-based retrieval may be susceptible to search-engine optimization (SEO) attacks, where adversaries promote malicious content by introducing adversarial passages to corpora. Prior work has shown such SEO is feasible, mostly demonstrating attacks against retrieval-integrated systems (e.g., RAG). Yet, these consider relaxed SEO threat models (e.g., targeting single queries), use baseline attack methods, and provide small-scale retrieval evaluation, thus obscuring our comprehensive understanding of retrievers' worst-case behavior. This work aims to faithfully and thoroughly assess retrievers' robustness, paving a path to uncover factors related to their susceptibility to SEO. To this end, we, first, propose the GASLITE attack for generating adversarial passages, that$\unicode{x2013}$without relying on the corpus content or modifying the model$\unicode{x2013}$carry adversary-chosen information while achieving high retrieval ranking, consistently outperforming prior approaches. Second, using GASLITE, we extensively evaluate retrievers' robustness, testing nine advanced models under varied threat models, while focusing on pertinent adversaries targeting queries on a specific concept (e.g., a public figure). Amongst our findings: retrievers are highly vulnerable to SEO against concept-specific queries, even under negligible poisoning rates (e.g., $\geq$0.0001% of the corpus), while generalizing across different corpora and query distributions; single-query SEO is completely solved by GASLITE; adaptive attacks demonstrate bypassing common defenses; [...]

cs.CR↗

arXiv2024

Impactful Bit-Flip Search on Full-precision Models

Neural networks have shown remarkable performance in various tasks, yet they remain susceptible to subtle changes in their input or model parameters. One particularly impactful vulnerability arises through the Bit-Flip Attack (BFA), where flipping a small number of critical bits in a model's parameters can severely degrade its performance. A common technique for inducing bit flips in DRAM is the Row-Hammer attack, which exploits frequent uncached memory accesses to alter data. Identifying susceptible bits can be achieved through exhaustive search or progressive layer-by-layer analysis, especially in quantized networks. In this work, we introduce Impactful Bit-Flip Search (IBS), a novel method for efficiently pinpointing and flipping critical bits in full-precision networks. Additionally, we propose a Weight-Stealth technique that strategically modifies the model's parameters in a way that maintains the float values within the original distribution, thereby bypassing simple range checks often used in tamper detection.

cs.LG↗

arXiv2024

Privacy-Preserving Collaborative Genomic Research: A Real-Life Deployment and Vision

The data revolution holds significant promise for the health sector. Vast amounts of data collected from individuals will be transformed into knowledge, AI models, predictive systems, and best practices. One area of health that stands to benefit greatly is the genomic domain. Progress in AI, machine learning, and data science has opened new opportunities for genomic research, promising breakthroughs in personalized medicine. However, increasing awareness of privacy and cybersecurity necessitates robust solutions to protect sensitive data in collaborative research. This paper presents a practical deployment of a privacy-preserving framework for genomic research, developed in collaboration with Lynx$.$MD, a platform for secure health data collaboration. The framework addresses critical cybersecurity and privacy challenges, enabling the privacy-preserving sharing and analysis of genomic data while mitigating risks associated with data breaches. By integrating advanced privacy-preserving algorithms, the solution ensures the protection of individual privacy without compromising data utility. A unique feature of the system is its ability to balance trade-offs between data sharing and privacy, providing stakeholders tools to quantify privacy risks and make informed decisions. Implementing the framework within Lynx$.$MD involves encoding genomic data into binary formats and applying noise through controlled perturbation techniques. This approach preserves essential statistical properties of the data, facilitating effective research and analysis. Moreover, the system incorporates real-time data monitoring and advanced visualization tools, enhancing user experience and decision-making. The paper highlights the need for tailored privacy attacks and defenses specific to genomic data. Addressing these challenges fosters collaboration in genomic research, advancing personalized medicine and public health.

cs.CR↗

arXiv2024

Group-based Robustness: A General Framework for Customized Robustness in the Real World

Machine-learning models are known to be vulnerable to evasion attacks that perturb model inputs to induce misclassifications. In this work, we identify real-world scenarios where the true threat cannot be assessed accurately by existing attacks. Specifically, we find that conventional metrics measuring targeted and untargeted robustness do not appropriately reflect a model's ability to withstand attacks from one set of source classes to another set of target classes. To address the shortcomings of existing methods, we formally define a new metric, termed group-based robustness, that complements existing metrics and is better-suited for evaluating model performance in certain attack scenarios. We show empirically that group-based robustness allows us to distinguish between models' vulnerability against specific threat models in situations where traditional robustness metrics do not apply. Moreover, to measure group-based robustness efficiently and accurately, we 1) propose two loss functions and 2) identify three new attack strategies. We show empirically that with comparable success rates, finding evasive samples using our new loss functions saves computation by a factor as large as the number of targeted classes, and finding evasive samples using our new attack strategies saves time by up to 99\% compared to brute-force search methods. Finally, we propose a defense method that increases group-based robustness by up to 3.52$\times$.

cs.LG↗

arXiv2024

Redesigning Traffic Signs to Mitigate Machine-Learning Patch Attacks

Traffic-Sign Recognition (TSR) is a critical safety component for autonomous driving. Unfortunately, however, past work has highlighted the vulnerability of TSR models to physical-world attacks, through low-cost, easily deployable adversarial patches leading to misclassification. To mitigate these threats, most defenses focus on altering the training process or modifying the inference procedure. Still, while these approaches improve adversarial robustness, TSR remains susceptible to attacks attaining substantial success rates. To further the adversarial robustness of TSR, this work offers a novel approach that redefines traffic-sign designs to create signs that promote robustness while remaining interpretable to humans. Our framework takes three inputs: (1) A traffic-sign standard along with modifiable features and associated constraints; (2) A state-of-the-art adversarial training method; and (3) A function for efficiently synthesizing realistic traffic-sign images. Using these user-defined inputs, the framework emits an optimized traffic-sign standard such that traffic signs generated per this standard enable training TSR models with increased adversarial robustness. We evaluate the effectiveness of our framework via a concrete implementation, where we allow modifying the pictograms (i.e., symbols) and colors of traffic signs. The results show substantial improvements in robustness -- with gains of up to 16.33%--24.58% in robust accuracy over state-of-the-art methods -- while benign accuracy is even improved. Importantly, a user study also confirms that the redesigned traffic signs remain easily recognizable and to human observers. Overall, the results highlight that carefully redesigning traffic signs can significantly enhance TSR system robustness without compromising human interpretability.

cs.CR↗

arXiv2023

The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentations

To help adversarial examples generalize from surrogate machine-learning (ML) models to targets, certain transferability-based black-box evasion attacks incorporate data augmentations (e.g., random resizing). Yet, prior work has explored limited augmentations and their composition. To fill the gap, we systematically studied how data augmentation affects transferability. Specifically, we explored 46 augmentation techniques originally proposed to help ML models generalize to unseen benign samples, and assessed how they impact transferability, when applied individually or composed. Performing exhaustive search on a small subset of augmentation techniques and genetic search on all techniques, we identified augmentation combinations that help promote transferability. Extensive experiments with the ImageNet and CIFAR-10 datasets and 18 models showed that simple color-space augmentations (e.g., color to greyscale) attain high transferability when combined with standard augmentations. Furthermore, we discovered that composing augmentations impacts transferability mostly monotonically (i.e., more augmentations $\rightarrow$ $\ge$transferability). We also found that the best composition significantly outperformed the state of the art (e.g., 91.8% vs. $\le$82.5% average transferability to adversarially trained targets on ImageNet). Lastly, our theoretical analysis, backed by empirical evidence, intuitively explains why certain augmentations promote transferability.

cs.CV↗

arXiv2022

Scalable Verification of GNN-based Job Schedulers

Recently, Graph Neural Networks (GNNs) have been applied for scheduling jobs over clusters, achieving better performance than hand-crafted heuristics. Despite their impressive performance, concerns remain over whether these GNN-based job schedulers meet users' expectations about other important properties, such as strategy-proofness, sharing incentive, and stability. In this work, we consider formal verification of GNN-based job schedulers. We address several domain-specific challenges such as networks that are deeper and specifications that are richer than those encountered when verifying image and NLP classifiers. We develop vegas, the first general framework for verifying both single-step and multi-step properties of these schedulers based on carefully designed algorithms that combine abstractions, refinements, solvers, and proof transfer. Our experimental results show that vegas achieves significant speed-up when verifying important properties of a state-of-the-art GNN-based scheduler compared to previous methods.

cs.AI↗

arXiv2022

Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks

We propose new, more efficient targeted white-box attacks against deep neural networks. Our attacks better align with the attacker's goal: (1) tricking a model to assign higher probability to the target class than to any other class, while (2) staying within an $ε$-distance of the attacked input. First, we demonstrate a loss function that explicitly encodes (1) and show that Auto-PGD finds more attacks with it. Second, we propose a new attack method, Constrained Gradient Descent (CGD), using a refinement of our loss function that captures both (1) and (2). CGD seeks to satisfy both attacker objectives -- misclassification and bounded $\ell_{p}$-norm -- in a principled manner, as part of the optimization, instead of via ad hoc post-processing techniques (e.g., projection or clipping). We show that CGD is more successful on CIFAR10 (0.9--4.2%) and ImageNet (8.6--13.6%) than state-of-the-art attacks while consuming less time (11.4--18.8%). Statistical tests confirm that our attack outperforms others against leading defenses on different datasets and values of $ε$.

cs.LG↗

arXiv2021

Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable Bytes

Motivated by the transformative impact of deep neural networks (DNNs) in various domains, researchers and anti-virus vendors have proposed DNNs for malware detection from raw bytes that do not require manual feature engineering. In this work, we propose an attack that interweaves binary-diversification techniques and optimization frameworks to mislead such DNNs while preserving the functionality of binaries. Unlike prior attacks, ours manipulates instructions that are a functional part of the binary, which makes it particularly challenging to defend against. We evaluated our attack against three DNNs in white- and black-box settings, and found that it often achieved success rates near 100%. Moreover, we found that our attack can fool some commercial anti-viruses, in certain cases with a success rate of 85%. We explored several defenses, both new and old, and identified some that can foil over 80% of our evasion attempts. However, these defenses may still be susceptible to evasion by attacks, and so we advocate for augmenting malware-detection systems with methods that do not rely on machine learning.

cs.CR↗

arXiv2019

$n$-ML: Mitigating Adversarial Examples via Ensembles of Topologically Manipulated Classifiers

This paper proposes a new defense called $n$-ML against adversarial examples, i.e., inputs crafted by perturbing benign inputs by small amounts to induce misclassifications by classifiers. Inspired by $n$-version programming, $n$-ML trains an ensemble of $n$ classifiers, and inputs are classified by a vote of the classifiers in the ensemble. Unlike prior such approaches, however, the classifiers in the ensemble are trained specifically to classify adversarial examples differently, rendering it very difficult for an adversarial example to obtain enough votes to be misclassified. We show that $n$-ML roughly retains the benign classification accuracies of state-of-the-art models on the MNIST, CIFAR10, and GTSRB datasets, while simultaneously defending against adversarial examples with better resilience than the best defenses known to date and, in most cases, with lower classification-time overhead.

cs.CV↗

arXiv2019

A General Framework for Adversarial Examples with Objectives

Images perturbed subtly to be misclassified by neural networks, called adversarial examples, have emerged as a technically deep challenge and an important concern for several application domains. Most research on adversarial examples takes as its only constraint that the perturbed images are similar to the originals. However, real-world application of these ideas often requires the examples to satisfy additional objectives, which are typically enforced through custom modifications of the perturbation process. In this paper, we propose adversarial generative nets (AGNs), a general methodology to train a generator neural network to emit adversarial examples satisfying desired objectives. We demonstrate the ability of AGNs to accommodate a wide range of objectives, including imprecise ones difficult to model, in two application domains. In particular, we demonstrate physical adversarial examples---eyeglass frames designed to fool face recognition---with better robustness, inconspicuousness, and scalability than previous approaches, as well as a new attack to fool a handwritten-digit classifier.

cs.CV↗