2 citations · 2 across the 5 of their papers we have counts for
6 papers
Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives
Zecheng Wang, Deyuan Liu, Chunshan Li +5
Standard negative log-likelihood (NLL) for Supervised Fine-Tuning (SFT) applies uniform token-level weighting. This rigidity creates a two-fold failure mode: (i) overemphasizing lo…
Stealth Fine-Tuning: Efficiently Breaking Alignment in RVLMs Using Self-Generated CoT
Le Yu, Zhengyue Zhao, Yawen Zheng +1
Reasoning-augmented Vision-Language Models (RVLMs) rely on safety alignment to prevent harmful behavior, yet their exposed chain-of-thought (CoT) traces introduce new attack surfac…
Adversarially Robust AI-Generated Image Detection for Free: An Information Theoretic Perspective
Ruixuan Zhang, He Wang, Zhengyu Zhao +4
Rapid advances in Artificial Intelligence Generated Images (AIGI) have facilitated malicious use, such as forgery and misinformation. Therefore, numerous methods have been proposed…
CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
Songlong Xing, Zhengyu Zhao, Nicu Sebe
Despite its prevalent use in image-text matching tasks in a zero-shot manner, CLIP has been shown to be highly vulnerable to adversarial perturbations added onto images. Recent stu…
Improving Adversarial Robustness in Android Malware Detection by Reducing the Impact of Spurious Correlations
Hamid Bostani, Zhengyu Zhao, Veelasha Moonsamy
Machine learning (ML) has demonstrated significant advancements in Android malware detection (AMD); however, the resilience of ML against realistic evasion attacks remains a major…
Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection
Weijie Wang, Zhengyu Zhao, Nicu Sebe +1
Malicious use of deepfakes leads to serious public concerns and reduces people's trust in digital media. Although effective deepfake detectors have been proposed, they are substant…