10 papers
Cooldown Landmines: Cross-Tenant Interference Attacks on LLM Gateways
Yudong Gao, Linghan Chen, Wenhan Wu +8
LLM gateways enforce separate tenant quotas while sharing model deployments and cooldown records that temporarily exclude failing backends. However, a tenant's request failure can…
Trust the Brand, Lose Control: How Identity Hijacks LLM Agent Orchestration
Xutao Mao, Rui Qian, Linghan Chen +5
LLM agents now execute tasks end to end with permission to change real systems and increasingly orchestrate subagents that differ in capability and cost. Prior work treats the choi…
"You're Right, Let Me Fix It": How LLM Agents Damage Correct Work When Falsely Accused
Xutao Mao, Rui Qian, Longxiang Wang +6
LLM agents increasingly keep working after a task succeeds as they resume after compaction or take over handoffs. Their finished work keeps receiving follow-up input that sometimes…
Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement
Xutao Mao, Jianing Zhu, Jinman Zhao +4
Reinforcement learning (RL) has substantially improved the reasoning capabilities of vision-language models (VLMs), yet it can induce chain-of-thought (CoT) obfuscation, an operati…
Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents
Xutao Mao, Liangjie Zhao, Leyao Wang +6
Self-improving personal agents write profiles, memories, and reusable skills that carry over from one chat to the next. Prior works ask whether a model agrees with the user in its…
MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems
Haobo Zhang, Xutao Mao, Guangyuan Dong +5
Memory-backed agents need provenance that can survive leaked or migrated snapshots, where logs, visible outputs, and trusted metadata may be absent. We propose MemMark, a state-evo…
Benchmarking Fake Voice Detection in the Fake Voice Generation Arms Race
Xutao Mao, Ke Li, Cameron Baird +2
The rapid advancement of fake voice generation technology has ignited a race with detection systems, creating an urgent need to secure the audio ecosystem. However, existing benchm…
ParlAI Vote: A Web Platform for Analyzing Gender and Political Bias in Large Language Models
Wenjie Lin, Hange Liu, Yingying Zhuang +5
We present ParlAI Vote, an interactive web platform for exploring European Parliament debates and votes, and for testing LLMs on vote prediction and bias analysis. This web system…
Towards Bridging Review Sparsity in Recommendation with Textual Edge Graph Representation
Leyao Wang, Xutao Mao, Xuhui Zhan +5
Textual reviews enrich recommender systems with fine-grained preference signals and enhanced explainability. However, in real-world scenarios, users rarely leave reviews, resulting…
MindVote: When AI Meets the Wild West of Social Media Opinion
Xutao Mao, Ezra Xuanru Tao, Leyao Wang
Large Language Models (LLMs) are increasingly used as scalable tools for pilot testing, predicting public opinion distributions before deploying costly surveys. To serve as effecti…