3 papers
cs.LG2025
FedThief: Harming Others to Benefit Oneself in Self-Centered Federated Learning
Xiangyu Zhang, Mang Ye
In federated learning, participants' uploaded model updates cannot be directly verified, leaving the system vulnerable to malicious attacks. Existing attack strategies have adversa…
cs.AI2025
RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models
Jianhao Chen, Mayi Xu, Haoyang Chen +6
Large Reasoning Models (LRMs) face a distinct safety vulnerability: their internal reasoning chains may generate harmful content even when the final output appears benign. To addre…
cs.SE2025
Beyond C/C++: Probabilistic and LLM Methods for Next-Generation Software Reverse Engineering
Zhuo Zhuo, Xiangyu Zhang
This proposal discusses the growing challenges in reverse engineering modern software binaries, particularly those compiled from newer system programming languages such as Rust, Go…