2 citations · 2 across the 19 of their papers we have counts for
22 papers
Last Secure Code Benchmark: Is the Code You Vibe Secure?
Tianyi Wu, Chao Ge, Peng Chen +12
AI coding agents now write much of the code that ships, yet whether that code is secure remains unclear. We introduce the Last Secure Code Benchmark, a comprehensive evaluation of…
Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry
Shengfang Zhai, Leo Marchyok, Yuling Shi +4
Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive LMs, offering advantages such as parallel generation and bidirectional…
Robustifying Vision-Language Models via Test-Time Prompt Adaptation
Xingyu Zhu, Huanshen Wu, Shuo Wang +4
Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations. Existing tes…
BadDLM: Backdooring Diffusion Language Models with Diverse Targets
Shengfang Zhai, Xiaoyang Ji, Yuling Shi +6
Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive (AR) language models, enabling parallel generation and bidirectional co…
Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection
Meng Chen, Kun Wang, Li Lu +2
Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond…
Gym-V: A Unified Vision Environment System for Agentic Vision Research
Fanqing Meng, Lingxiao Du, Jiawei Gu +9
As agentic systems increasingly rely on reinforcement learning from verifiable rewards, standardized ``gym'' infrastructure has become essential for rapid iteration, reproducibilit…
MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
Yuhao Wang, Shengfang Zhai, Guanghao Jin +3
Large Language Model (LLM)-based agents employ external and internal memory systems to handle complex, goal-oriented tasks, yet this exposes them to severe extraction attacks, and…
Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model
Tianyi Wu, Mingzhe Du, Yue Liu +4
Large language models (LLMs) are increasingly used in software development, yet their tendency to generate insecure code remains a major barrier to real-world deployment. Existing…
Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models
Linhao Zhong, Linyu Wu, Bozhen Fang +6
Diffusion Language Models (DLMs) offer a promising alternative for language modeling by enabling parallel decoding through iterative refinement. However, most DLMs rely on hard bin…
Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG Systems
Weijie Wang, Peizhuo Lv, Yan Wang +7
Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a key technique for enhancing Large Language Models (LLMs) with proprietary Knowledge Graphs (KGs) in knowledge-inten…
The Oracle and The Prism: A Decoupled and Efficient Framework for Generative Recommendation Explanation
Jiaheng Zhang, Daqiang Zhang
The integration of Large Language Models (LLMs) into explainable recommendation systems often leads to a performance-efficiency trade-off in end-to-end architectures, where joint o…
ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu +8
LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate…
SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking
Wenyuan Yang, Yichen Sun, Changzheng Chen +4
Large-scale vision-language models, especially CLIP, have demonstrated remarkable performance across diverse downstream tasks. Soft prompts, as carefully crafted modules that effic…
DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
Zherui Li, Zheng Nie, Zhenhong Zhou +7
The rapid advancement of Diffusion Large Language Models (dLLMs) introduces unprecedented vulnerabilities that are fundamentally distinct from Autoregressive LLMs, stemming from th…
ExtendAttack: Attacking Servers of LRMs via Extending Reasoning
Zhenhao Zhu, Yue Liu, Zhiwei Xu +9
Large Reasoning Models (LRMs) have demonstrated promising performance in complex tasks. However, the resource-consuming reasoning processes may be exploited by attackers to malicio…
TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models
Yang Dai, Oubo Ma, Longfei Zhang +6
Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabilities against backdoor attacks a…
Efficient Reasoning via Chain of Unconscious Thought
Ruihan Gong, Yue Liu, Wenjie Qu +11
Large Reasoning Models (LRMs) achieve promising performance but compromise token efficiency due to verbose reasoning processes. Unconscious Thought Theory (UTT) posits that complex…
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
Yue Liu, Shengfang Zhai, Mingzhe Du +9
To enhance the safety of VLMs, this paper introduces a novel reasoning-based VLM guard model dubbed GuardReasoner-VL. The core idea is to incentivize the guard model to deliberativ…
Geneshift: Impact of different scenario shift on Jailbreaking LLM
Tianyi Wu, Zhiwei Xue, Yue Liu +3
Jailbreak attacks, which aim to cause LLMs to perform unrestricted behaviors, have become a critical and challenging direction in AI safety. Despite achieving the promising attack…
Efficient Inference for Large Reasoning Models: A Survey
Yue Liu, Jiaying Wu, Yufei He +11
Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in solving complex…
Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning
Tianyi Wu, Jingwei Ni, Bryan Hooi +5
Instruction fine-tuning (IFT) can increase the informativeness of large language models (LLMs), but may reduce their truthfulness. This trade-off arises because IFT steers LLMs to…
GuardReasoner: Towards Reasoning-based LLM Safeguards
Yue Liu, Hongcheng Gao, Shengfang Zhai +9
As LLMs increasingly impact safety-critical applications, ensuring their safety using guardrails remains a key challenge. This paper proposes GuardReasoner, a new safeguard for LLM…