Related papers: Stop Testing Attacks, Start Diagnosing Defenses: T…

Multi-agent LLM systems are entering production -- processing documents, managing workflows, acting on behalf of users -- yet their resilience to prompt injection is still evaluated with a single binary: did the attack succeed? This leaves…

This paper presents LProtector, an automated vulnerability detection system for C/C++ codebases driven by the large language model (LLM) GPT-4o and Retrieval-Augmented Generation (RAG). As software complexity grows, traditional methods face…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and…

The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily…

Large Language Models (LLMs) have revolutionized artificial intelligence and machine learning through their advanced text processing and generating capabilities. However, their widespread deployment has raised significant safety and…

Multi-Agent Debate (MAD), leveraging collaborative interactions among Large Language Models (LLMs), aim to enhance reasoning capabilities in complex tasks. However, the security implications of their iterative dialogues and role-playing…

Jailbreak attacks induce Large Language Models (LLMs) to generate harmful responses, posing severe misuse threats. Though research on jailbreak attacks and defenses is emerging, there is no consensus on evaluating jailbreaks, i.e., the…

The attack surface of a multimodal large language model (MLLM) is language-dependent in ways that reveal the mechanistic structure of alignment failures. We present the first systematic cross-lingual, multimodal red-teaming study comparing…

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…

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…

Despite various approaches being employed to detect vulnerabilities, the number of reported vulnerabilities shows an upward trend over the years. This suggests the problems are not caught before the code is released, which could be caused…

While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after…

As the application of large language models continues to expand in various fields, it poses higher challenges to the effectiveness of identifying harmful content generation and guardrail mechanisms. This research aims to evaluate the…

With the rapid advancement of Large Vision-Language Models (LVLMs), ensuring their safety has emerged as a crucial area of research. This survey provides a comprehensive analysis of LVLM safety, covering key aspects such as attacks,…

Large language models (LLMs) can detect software vulnerabilities, but how do they actually identify vulnerable code? We address this question using mechanistic interpretability; analyzing the internal computations of a neural network to…

The deployment of large language models (LLMs) as interactive agents has exposed a category of behavioral failure that prevailing terminology, principally hallucination, fails to adequately characterize. This paper introduces LLM Psychosis…

GPT-4V has attracted considerable attention due to its extraordinary capacity for integrating and processing multimodal information. At the same time, its ability of face recognition raises new safety concerns of privacy leakage. Despite…

The integration of large language models (LLMs) into electronic design automation (EDA) workflows has introduced powerful capabilities for RTL generation, verification, and design optimization, but also raises critical security concerns.…

We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of threat hunting: given a database of raw Windows event logs with no guided questions or…

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…