相关论文: Large-Scale Analysis of Style Injection by Relativ…

Reinforcement learning (RL) has emerged as an effective approach for enhancing the reasoning capabilities of large language models (LLMs), especially in scenarios where supervised fine-tuning (SFT) falls short due to limited…

Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-language rubrics and validated on benchmarks. We identify a previously under-recognized vulnerability in…

Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated notable success in enhancing the reasoning performance of large language models (LLMs). However, recent studies reveal that while current RLVR methods improve sampling…

We demonstrate the first downgrade attacks against RPKI. The key design property in RPKI that allows our attacks is the tradeoff between connectivity and security: when networks cannot retrieve RPKI information from publication points, they…

Although Large Reasoning Models (LRMs) have progressed in solving complex problems, their chain-of-thought (CoT) reasoning often contains harmful content that can persist even when the final responses appear safe. We show that this issue…

Carriage return (CR) and line feed (LF), also known as CRLF injection is a type of vulnerability that allows a hacker to enter special characters into a web application, altering its operation or confusing the administrator. Log poisoning…

Recent generative engine optimisation (GEO) research has shown that prompt-injection attacks can push a target product to the top of an LLM's recommendation list, with the strongest attacks reporting around $80\%$ success and raising…

The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…

Address Space Layout Randomization (ASLR) is one of the most prominently deployed mitigations against memory corruption attacks. ASLR randomly shuffles program virtual addresses to prevent attackers from knowing the location of program…

Proximal policy optimization (PPO) is one of the most popular deep reinforcement learning (RL) methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, as a model-free RL method, the success of PPO…

Web applications often include third-party content and scripts to personalize a user's online experience. These scripts have unrestricted access to a user's private data stored in the browser's persistent storage like cookies, localstorage…

As the Routing Protocol for Low Power and Lossy Networks (RPL) became the standard for routing in the Internet of Things (IoT) networks, many researchers had investigated the security aspects of this protocol. However, no work (to the best…

The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection attacks. In these attacks, malicious instructions embedded…

The proliferation of agentic AI coding assistants, including Claude Code, GitHub Copilot, Cursor, and emerging skill-based architectures, has fundamentally transformed software development workflows. These systems leverage Large Language…

This work considers a black-box threat model in which adversaries attempt to propagate arbitrary non-relevant content in search. We show that retrievers, rerankers, and LLM relevance judges are all highly vulnerable to attacks that enable…

In today's world, Web applications play a very important role in individual life as well as in any country's development. Web applications have gone through a very rapid growth in the recent years and their adoption is moving faster than…

Reinforcement learning (RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives. Proximal policy optimization (PPO) is a popular choice of method for policy optimization. While…

We show that Web and Research Agents (WRAs) -- language-model-based systems that investigate complex topics on the Internet -- are vulnerable to inference attacks by passive network observers. Deployment of WRAs \emph{locally} by…

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Online and offline RLHF methods, such as PPO and DPO, have been highly successful in aligning AI with human preferences. Despite their success, however, these methods suffer from fundamental limitations: (a) Models trained with RLHF can…