Related papers: SAGE: Signal-Amplified Guided Embeddings for LLM-b…

The growth of open-source software has increased the risk of hidden vulnerabilities that can affect downstream software applications. This concern is further exacerbated by software vendors' practice of silently releasing security patches…

Recent studies have explored large language models for time-series anomaly detection, yet existing approaches often rely on a single general-purpose model to directly infer anomaly indices or intervals, limiting controllability,…

Sharpness-aware minimization (SAM) seeks the minima with a flat loss landscape to improve the generalization performance in machine learning tasks, including fine-tuning. However, its extra parameter perturbation step doubles the…

Large Language Models (LLMs) have driven substantial progress in artificial intelligence in recent years, exhibiting impressive capabilities across a wide range of tasks, including mathematical problem-solving. Inspired by the success of…

The rapid advancement of software development practices has introduced challenges in ensuring quality and efficiency across the software engineering (SE) lifecycle. As SE systems grow in complexity, traditional approaches often fail to…

The rapid growth in the parameter scale of large language models (LLMs) has created a high demand for efficient compression techniques. As a hardware-agnostic and highly compatible technique, low-rank compression has been widely adopted.…

Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety:…

Large language models (LLMs) have shown remarkable capabilities in natural language processing tasks, yet their application in hardware security verification remains limited due to scarcity of publicly available hardware description…

Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models, yet scalable training remains a significant challenge. We introduce a suite of 256 SAEs, trained on each…

Accurate anomaly detection is critical in vision-based infrastructure inspection, where it helps prevent costly failures and enhances safety. Self-Supervised Learning (SSL) offers a promising approach by learning robust representations from…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Context: Software vulnerabilities pose significant security threats to software systems, especially as software is increasingly used across many areas of daily life, including health, government, and finance. Recently, transformer-based…

Sparse autoencoders (SAEs) are a useful tool for uncovering human-interpretable features in the activations of large language models (LLMs). While some expect SAEs to find the true underlying features used by a model, our research shows…

Automated detection of software vulnerabilities is critical for enhancing security, yet existing methods often struggle with the complexity and diversity of modern codebases. In this paper, we introduce EnStack, a novel ensemble stacking…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

The widespread practice of fine-tuning open-source Vision-Language Models (VLMs) raises a critical security concern: jailbreak vulnerabilities in base models may persist in downstream variants, enabling transferable attacks across…

Sparse autoencoders (SAEs) are commonly used to interpret the internal activations of large language models (LLMs) by mapping them to human-interpretable concept representations. While existing evaluations of SAEs focus on metrics such as…

Attack graphs (AG) are used to assess pathways availed by cyber adversaries to penetrate a network. State-of-the-art approaches for AG generation focus mostly on deriving dependencies between system vulnerabilities based on network scans…

The application of Artificial Intelligence has become a powerful approach to detecting software vulnerabilities. However, effective vulnerability detection relies on accurately capturing the semantic structure of code and its contextual…

Large Language Models (LLMs) serve as the backbone of modern AI systems, yet they remain susceptible to adversarial jailbreak attacks. Consequently, robust detection of such malicious inputs is paramount for ensuring model safety.…