6 papers
When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments
Chong Zhang, Xinyi Liu, Zhongmou Zhang +10
Can AI Agents simulate real-world trading environments to investigate the impact of external factors on stock trading activities (e.g., macroeconomics, policy changes, company fund…
Semantic-Preserving Prompt Hijacking: A Black-Box Adversarial Attack on Auto-Prompt Optimization
Chong Zhang, Xiang Li, Jia Wang +3
LLMs increasingly integrate auto-suggestion optimization modules, enabling them to rewrite and display user input before generating the final response. While this design aims to en…
Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs
Xiang Li, Chong Zhang, Jia Wang +3
Current jailbreak attacks on large language models (LLMs) predominantly rely on LLMs themselves to generate adversarial prompts, creating a critical efficiency bottleneck: each att…
Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms
Chong Zhang, Xiang Li, Jia Wang +2
The robustness of deep neural networks is crucial for safety-critical deployments, yet existing evaluation methods are often attack-dependent and lack interpretability. We propose…
StealthMark: Harmless and Stealthy Ownership Verification for Medical Segmentation via Uncertainty-Guided Backdoors
Qinkai Yu, Chong Zhang, Gaojie Jin +11
Annotating medical data for training AI models is often costly and limited due to the shortage of specialists with relevant clinical expertise. This challenge is further compounded…
Performance is not All You Need: Sustainability Considerations for Algorithms
Xiang Li, Chong Zhang, Hongpeng Wang +3
This work focuses on the high carbon emissions generated by deep learning model training, specifically addressing the core challenge of balancing algorithm performance and energy c…