1 citations · 1 across the 4 of their papers we have counts for
12 papers
Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
Xu Li, Simon Yu, Minzhou Pan +5
LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in m…
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
Jaylen Jones, Zhehao Zhang, Yuting Ning +6
Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unintended behaviors that deviate from exp…
Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents
Tianci Xue, Zeyi Liao, Tianneng Shi +5
Real-world digital environments are highly diverse and dynamic. These characteristics cause agents to frequently encounter unseen environments and distribution shifts, making conti…
MalTool: Malicious Tool Attacks on LLM Agents
Yuepeng Hu, Yuqi Jia, Mengyuan Li +2
In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user inadvertently installs the tool and the LLM agent selects it during task ex…
Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities
Changdae Oh, Seongheon Park, To Eun Kim +8
Uncertainty quantification (UQ) for large language models (LLMs) is a key building block for safety guardrails of daily LLM applications. Yet, even as LLM agents are increasingly d…
Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence
Bofan Gong, Shiyang Lai, James Evans +1
Polysemanticity is pervasive in language models and remains a major challenge for interpretation and model behavioral control. Leveraging sparse autoencoders (SAEs), we map the pol…