Tianqing Zhu

MARCO: The Radioactive Watermark for Protein Generative Models

LiBRA: Detection-Aware Image Watermark Removal via Bidirectional Latent Optimization

First Token Matters: Understanding Safety Collapse in Large Reasoning Models

RISA: Response Inspection and Selective Actions for Refusal Calibration in Large Language Models

BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes

Beyond Her: Safety Dynamics in Role-play AI Companions

Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis

When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions

WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation

CSC: Turning the Adversary's Poison against Itself

Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking

Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor

ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery

Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation

Osmosis Distillation: Model Hijacking with the Fewest Samples

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction

Turning Black Box into White Box: Dataset Distillation Leaks

Forgetting Similar Samples: Can Machine Unlearning Do it Better?

Black-Box Auditing of Quantum Model: Lifted Differential Privacy with Quantum Canaries

Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection

When Harmless Words Harm: A New Threat to LLM Safety via Conceptual Triggers