相关论文: LLM Safety From Within: Detecting Harmful Content …

Insider threat detection aims to identify malicious user behavior by analyzing logs that record user interactions. Due to the lack of fine-grained behavior-level annotations, detecting specific behavior-level anomalies within user behavior…

Ransomware's escalating sophistication necessitates tamper-resistant, off-host detection solutions that capture deep disk activity beyond the reach of a compromised operating system. Existing detection systems use host/kernel signals or…

This work addresses the computational challenge of enforcing privacy for agentic Large Language Models (LLMs), where privacy is governed by the contextual integrity framework. Indeed, existing defenses rely on LLM-mediated checking stages…

This paper addresses the critical challenge of deriving interpretable confidence scores from generative language models (LLMs) when applied to multi-label content safety classification. While models like LLaMA Guard are effective for…

While explicit Chain-of-Thought (CoT) empowers large reasoning models (LRMs), it enables the generation of riskier final answers. Current alignment paradigms primarily rely on externally enforced compliance, optimizing models to detect…

Large Language Models (LLMs) have emerged as a popular choice in vulnerability detection studies given their foundational capabilities, open source availability, and variety of models, but have limited scalability due to extensive compute…

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…

Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety…

As Large Language Models (LLMs) are deployed and integrated into thousands of applications, the need for scalable evaluation of how models respond to adversarial attacks grows rapidly. However, LLM security is a moving target: models…

Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-data performance of the full tune-then-deploy procedure. We…

Multi-agent LLM systems introduce a security risk in which sensitive information accessed by one agent can propagate through shared context and reappear in downstream outputs, even without explicit adversarial intent. We formalise this…

Controlling undesirable Large Language Model (LLM) behaviors, such as the generation of unsafe content or failing to adhere to safety guidelines, often relies on costly fine-tuning. Activation steering provides an alternative for…

Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying them, including bias,…

Machine learning (ML)-based network intrusion detection is susceptible to attacks that perturb malicious network flows to evade detection. Existing approaches to evaluating the robustness of these models rely on gradient-based optimization…

Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that…

Malicious content generated by large language models (LLMs) can pose varying degrees of harm. Although existing LLM-based moderators can detect harmful content, they struggle to assess risk levels and may miss lower-risk outputs. Accurate…

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

To enhance the safety of VLMs, this paper introduces a novel reasoning-based VLM guard model dubbed GuardReasoner-VL. The core idea is to incentivize the guard model to deliberatively reason before making moderation decisions via online RL.…

Large language models (LLMs) have brought significant advancements to code generation, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like GitHub, introduces…

Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful, biased and harmful responses poses significant risks, particularly in critical applications. This highlights the urgent need…