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

Reinforcement learning has become a central paradigm for improving LLM reasoning. However, existing methods use a single policy to produce both inference responses and training optimization trajectories. The objective conflict between…

Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…

Website fingerprinting attacks, which use statistical analysis on network traffic to compromise user privacy, have been shown to be effective even if the traffic is sent over anonymity-preserving networks such as Tor. The classical attack…

Bias in Large Language Models (LLMs) poses significant risks to trustworthiness, manifesting primarily as stereotypical biases (e.g., gender or racial stereotypes) and structural biases (e.g., lexical overlap or position preferences).…

Reinforcement learning for LLM reasoning has rapidly emerged as a prominent research area, marked by a significant surge in related studies on both algorithmic innovations and practical applications. Despite this progress, several critical…

Large language models (LLMs) benefit substantially from supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) in reasoning tasks. However, these recipes perform poorly in instruction-based molecular…

In this work, we perform a comprehensive analysis of the security of text input fields in web browsers. We find that browsers' coarse-grained permission model violates two security design principles: least privilege and complete mediation.…

Deep reinforcement learning (DRL) is one of the promising approaches for introducing robots into complicated environments. The recent remarkable progress of DRL stands on regularization of policy, which allows the policy to improve stably…

Modern web services increasingly rely on REST APIs. Effectively testing these APIs is challenging due to the vast search space to be explored, which involves selecting API operations for sequence creation, choosing parameters for each…

Nowadays, general object detectors like YOLO and Faster R-CNN as well as their variants are widely exploited in many applications. Many works have revealed that these detectors are extremely vulnerable to adversarial patch attacks. The…

Direct Preference Optimization (DPO) aligns language models using pairwise preference comparisons, offering a simple and effective alternative to Reinforcement Learning (RL) from human feedback. However, in many practical settings, training…

Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capability of Large Language Models (LLMs). Current RLVR approaches typically conduct training across all generated tokens, but neglect to explore…

Retrieval-augmented generation (RAG) systems put more and more emphasis on grounding their responses in user-generated content found on the Web, amplifying both their usefulness and their attack surface. Most notably, indirect prompt…

Large Reasoning Models (LRMs) employ reasoning to address complex tasks. Such explicit reasoning requires extended context lengths, resulting in substantially higher resource consumption. Prior work has shown that adversarially crafted…

The Resource Public Key Infrastructure (RPKI) secures the Internet's routing system by defining a complex trust and validation framework for certificates, Route Origin Authorizations (ROAs), manifests, and Certificate Revocation Lists…

We investigate robustness to strong data corruption in offline sparse reinforcement learning (RL). In our setting, an adversary may arbitrarily perturb a fraction of the collected trajectories from a high-dimensional but sparse Markov…

Rank-Biased Overlap (RBO) is a similarity measure for indefinite rankings: it is top-weighted, and can be computed when only a prefix of the rankings is known or when they have only some items in common. It is widely used for instance to…

Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks. Existing agentic memory attacks require privileged access or explicit…

Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world scenarios that can amplify backdoor threats. This paper…

Sequential Recommenders, which exploit dynamic user intents through interaction sequences, is vulnerable to adversarial attacks. While existing attacks primarily rely on data poisoning, they require large-scale user access or fake profiles…