6 papers
NNProxy: Efficient Training-Free Proxy Alignment for Black-Box Zero-Shot LLM-Generated Text Detection
Kahim Wong, Kemou Li, Haiwei Wu +1
LLM-generated text (LGT) detection is essential for reliable forensic analysis and for mitigating LLM misuse. Existing LGT detectors can generally be categorized into two broad cla…
FeatDistill: A Feature Distillation Enhanced Multi-Expert Ensemble Framework for Robust AI-generated Image Detection
Zhilin Tu, Kemou Li, Fengpeng Li +3
The rapid iteration and widespread dissemination of deepfake technology have posed severe challenges to information security, making robust and generalizable detection of AI-genera…
AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
Fengpeng Li, Kemou Li, Qizhou Wang +2
Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off. Robustness means the model fine-tuned by…
LLM Unlearning with LLM Beliefs
Kemou Li, Qizhou Wang, Yue Wang +4
Large language models trained on vast corpora inherently risk memorizing sensitive or harmful content, which may later resurface in their outputs. Prevailing unlearning methods gen…
FontGuard: A Robust Font Watermarking Approach Leveraging Deep Font Knowledge
Kahim Wong, Jicheng Zhou, Kemou Li +3
The proliferation of AI-generated content brings significant concerns on the forensic and security issues such as source tracing, copyright protection, etc, highlighting the need f…
DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
Fengpeng Li, Kemou Li, Haiwei Wu +2
To protect deep neural networks (DNNs) from adversarial attacks, adversarial training (AT) is developed by incorporating adversarial examples (AEs) into model training. Recent stud…