3 papers
cs.CR2026
Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin
Qishun Yang, Shu Yang, Difei Xu +2
To support sustained interactions and personalized assistance, agents use long-term memory to retain and combine user information across sessions. Reusing such memories can lead an…
cs.AI2026
Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty
Yipeng Zhao, Qishun Yang, Shenzhe Zhu +2
Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with chain-of-thought traces can…
cs.CV2026
Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
Qishun Yang, Shu Yang, Lijie Hu +1
Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or c…