Related papers: RedVisor: Reasoning-Aware Prompt Injection Defense…

Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt injection (PI) attacks. Defending against PI attacks faces two major issues: malicious…

Application designers have moved to integrate large language models (LLMs) into their products. However, many LLM-integrated applications are vulnerable to prompt injections. While attempts have been made to address this problem by building…

As large language models (LLMs) become integrated into various sensitive applications, prompt injection, the use of prompting to induce harmful behaviors from LLMs, poses an ever increasing risk. Prompt injection attacks can cause LLMs to…

Large Multimodal Models (LMMs) have recently demonstrated remarkable visual understanding performance on both vision-language and vision-centric tasks. However, they often fall short in integrating advanced, task-specific capabilities for…

Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale…

We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate their unsafe behaviours. Existing AI safety approaches often rely on costly human evaluation…

Large Language Model-based systems (LLM systems) are information and query processing systems that use LLMs to plan operations from natural-language prompts and feed the output of each successive step into the LLM to plan the next. This…

Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden instructions are planted in the corpora and hijack model…

Jailbreak attacks circumvent LLMs' built-in safeguards by concealing harmful queries within jailbreak prompts. While existing defenses primarily focus on mitigating the effects of jailbreak prompts, they often prove inadequate as jailbreak…

Large language models (LLMs) are increasingly deployed in real-world applications ranging from chatbots to agentic systems, where they are expected to process untrusted data and follow trusted instructions. Failure to distinguish between…

Multimodal Large Language Models (MLLMs) have achieved remarkable success, yet they remain prone to perception-related hallucinations in fine-grained tasks. This vulnerability arises from a fundamental limitation: their reasoning is largely…

Multi-modal large language models (MLLMs), capable of processing text, images, and audio, have been widely adopted in various AI applications. However, recent MLLMs integrating images and text remain highly vulnerable to coordinated…

Deploying large vision-language models (LVLMs) introduces a unique vulnerability: susceptibility to malicious attacks via visual inputs. However, existing defense methods suffer from two key limitations: (1) They solely focus on textual…

Automating Register Transfer Level (RTL) code generation using Large Language Models (LLMs) offers substantial promise for streamlining digital circuit design and reducing human effort. However, current LLM-based approaches face significant…

The widespread adoption of Large Language Models (LLMs) has revolutionized AI deployment, enabling autonomous and semi-autonomous applications across industries through intuitive language interfaces and continuous improvements in model…

Large Language Model (LLM) agents are increasingly integrated into critical systems, leveraging external tools to interact with the real world. However, this capability exposes them to Indirect Prompt Injection (IPI), where attackers embed…

Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream black-box jailbreak attacks on VLMs work by distributing…

The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs)…

Safety, security, and compliance are essential requirements when aligning large language models (LLMs). However, many seemingly aligned LLMs are soon shown to be susceptible to jailbreak attacks. These attacks aim to circumvent the models'…

Retrieval-augmented generation (RAG) systems can effectively mitigate the hallucination problem of large language models (LLMs),but they also possess inherent vulnerabilities. Identifying these weaknesses before the large-scale real-world…