pith. sign in

Tianqing Zhu

Identifiers

No identifiers captured yet.

Papers (12)

  1. Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis cs.CR · 2026 · author #6
  2. When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions cs.CR · 2026 · author #2
  3. WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation cs.CR · 2026 · author #5
  4. CSC: Turning the Adversary's Poison against Itself cs.CR · 2026 · author #4
  5. Fundus Image-based Glaucoma Screening via Retinal Knowledge-Oriented Dynamic Multi-Level Feature Integration cs.CV · 2026 · author #11
  6. Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking cs.CV · 2026 · author #3
  7. Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor cs.CR · 2026 · author #2
  8. Are LLMs Ready for Computer Science Education? A Cross-Domain, Cross-Lingual and Cognitive-Level Evaluation Using Professional Certification Exams cs.CY · 2026 · author #11
  9. From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration cs.MA · 2026 · author #4
  10. Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA cs.LG · 2024 · author #2
  11. Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions cs.LG · 2024 · author #2
  12. Differentially Private Query Learning: from Data Publishing to Model Publishing cs.CR · 2017 · author #1

Mentions

No mention provenance yet.

Frequent Coauthors