Related papers: Trust Me, Import This: Dependency Steering Attacks…

Large language models (LLMs) have been widely adopted in applications such as automated content generation and even critical decision-making systems. However, the risk of prompt injection allows for potential manipulation of LLM outputs.…

The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance. This creates a risk where third-party…

Large Language Models (LLMs) have shown impressive proficiency in code generation. Unfortunately, these models share a weakness with their human counterparts: producing code that inadvertently has security vulnerabilities. These…

Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…

Language models (LMs) are increasingly used in collaboration: multiple LMs trained by different parties collaborate through routing systems, multi-agent debate, model merging, and more. Critical safety risks remain in this decentralized…

With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…

The rapid adoption of large language models (LLMs) in multi-agent systems has highlighted their impressive capabilities in various applications, such as collaborative problem-solving and autonomous negotiation. However, the security…

Large-language-model coding tools are now mainstream in software engineering. But as these same tools move human effort up the development stack, they present fresh dangers: 10% of real prompts leak private data, 42% of generated snippets…

Multi-agent systems (MAS) powered by large language models (LLMs) increasingly adopt planner--executor architectures, where planners convert prompts into subtasks, roles, dependencies, and routing paths. This flexibility enables adaptive…

Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…

Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hide malicious instructions inside a dense, action-oriented skill that already functions as…

Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but whether they encode semantic operations producing those…

Even after fine-tuning and reinforcement learning, large language models (LLMs) can be difficult, if not impossible, to control reliably with prompts alone. We propose a new inference-time approach to enforcing syntactic and semantic…

Large Language Models (LLMs) are increasingly used as code assistants, yet their behavior when explicitly asked to generate insecure code remains poorly understood. While prior research has focused on unintended vulnerabilities, this study…

Large language models (LLMs) can generate executable code from natural language descriptions, but the resulting programs frequently contain bugs due to hallucinations. In the absence of formal specifications, existing approaches attempt to…

Large Language Models (LLMs) are being increasingly used in software engineering tasks, with an increased focus on bug report resolution over the past year. However, most proposed systems fail to properly handle uncertain or incorrect…

Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models. Controlled generation methods for DLMs, imported from autoregressive models, apply…

Large language models (LLMs) have succeeded significantly in various applications but remain susceptible to adversarial jailbreaks that void their safety guardrails. Previous attempts to exploit these vulnerabilities often rely on high-cost…

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange…

Activation steering offers a computationally efficient mechanism for controlling Large Language Models (LLMs) without fine-tuning. While effectively controlling target traits (e.g., persona), coherency degradation remains a major obstacle…