452 matches found
PYSEC-2025-53
vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...
CVE-2025-46570 vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel
vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...
System Prompt Extraction Attacks and Defenses in Large Language Models
The system prompt in Large Language Models LLMs plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become an emerging attack target. Recent studies have shown that...
Phare: a Safety Probe for Large Language Models
Ensuring the safety of large language models LLMs is critical for responsible deployment, yet existing evaluations often prioritize performance over identifying failure modes. We introduce Phare, a multilingual diagnostic framework to probe and evaluate LLM behavior across three critical...
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
Large language models LLMs have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit harmful outputs. Despite growing efforts in LLM safety research, existing evaluations are often fragmented, focused on...
Semantic-Preserving Adversarial Attacks on LLMs: an Adaptive Greedy Binary Search Approach
Large Language Models LLMs increasingly rely on automatic prompt engineering in graphical user interfaces GUIs to refine user inputs and enhance response accuracy. However, the diversity of user requirements often leads to unintended misinterpretations, where automated optimizations distort...
CoTGuard: Using Chain-Of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems
As large language models LLMs evolve into autonomous agents capable of collaborative reasoning and task execution, multi-agent LLM systems have emerged as a powerful paradigm for solving complex problems. However, these systems pose new challenges for copyright protection, particularly when...
Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models
State-of-the-art membership inference attacks MIAs typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models LLMs. As a result, prior research has either relied on weaker attacks that avoid training reference models e.g.,...
One Model Transfer to All: on Robust Jailbreak Prompts Generation against LLMs
Safety alignment in large language models LLMs is increasingly compromised by jailbreak attacks, which can manipulate these models to generate harmful or unintended content. Investigating these attacks is crucial for uncovering model vulnerabilities. However, many existing jailbreak strategies fa...
Invisible Tokens, Visible Bills: the Urgent Need to Audit Hidden Operations in Opaque LLM Services
Whitepaper called Invisible Tokens, Visible Bills: The Urgent Need To Audit Hidden Operations In Opaque LLM Services...
ACSE-Eval: Can LLMs Threat Model Real-World Cloud Infrastructure?
While Large Language Models have shown promise in cybersecurity applications, their effectiveness in identifying security threats within cloud deployments remains unexplored. This paper introduces AWS Cloud Security Engineering Eval, a novel dataset for evaluating LLMs cloud security threat...
Mapping the Future of AI Security
AI security is one of the most pressing challenges facing the world today. Artificial intelligence is extraordinarily powerful, and, especially considering the advent of Agentic AI, growing more so by the day. But it is for this reason that securing it is so important. AI handles massive amounts ...
When Safety Detectors Aren'T Enough: a Stealthy and Effective Jailbreak Attack on LLMs Via Steganographic Techniques
Jailbreak attacks pose a serious threat to large language models LLMs by bypassing built-in safety mechanisms and leading to harmful outputs. Studying these attacks is crucial for identifying vulnerabilities and improving model security. This paper presents a systematic survey of jailbreak method...
CAIN: Hijacking LLM-Humans Conversations Via a Two-Stage Malicious System Prompt Generation and Refining Framework
Large language models LLMs have advanced many applications, but are also known to be vulnerable to adversarial attacks. In this work, we introduce a novel security threat: hijacking AI-human conversations by manipulating LLMs' system prompts to produce malicious answers only to specific targeted...
Mitigating Fine-Tuning Risks in LLMs Via Safety-Aware Probing Optimization
The significant progress of large language models LLMs has led to remarkable achievements across numerous applications. However, their ability to generate harmful content has sparked substantial safety concerns. Despite the implementation of safety alignment techniques during the pre-training...
Advancing Security with Digital Twins: a Comprehensive Survey
The proliferation of electronic devices has greatly transformed every aspect of human life, such as communication, healthcare, transportation, and energy. Unfortunately, the global electronics supply chain is vulnerable to various attacks, including piracy of intellectual properties, tampering,...
Unlearning Isn'T Deletion: Investigating Reversibility of Machine Unlearning in LLMs
Unlearning in large language models LLMs is intended to remove the influence of specific data, yet current evaluations rely heavily on token-level metrics such as accuracy and perplexity. We show that these metrics can be misleading: models often appear to forget, but their original behavior can ...
CoTSRF: Utilize Chain of Thought As Stealthy and Robust Fingerprint of Large Language Models
Despite providing superior performance, open-source large language models LLMs are vulnerable to abusive usage. To address this issue, recent works propose LLM fingerprinting methods to identify the specific source LLMs behind suspect applications. However, these methods fail to provide stealthy...