From the 2 of 5 linked papers with an AI index.
5 papers
A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models
Xiangyu Yin, Tora Bodin, Rohan Menon +1
The paper evaluates five direction‑based inference‑time defenses for vision‑language models across multiple architectures, finding that no single method works best for all models a…
Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration
Xiangyu Yin, Jiaxu Liu, Zhen Chen +1
The paper identifies a systematic “margin cliff” that makes large language model unlearning vulnerable to relearn attacks and proposes Margin Calibration, a plug‑in method that add…
ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning
Xiangyu Yin, Yi Qi, Chih-Hong Cheng
Retrieval-Augmented Generation (RAG) improves large language model applications by grounding generation in retrieved evidence, but also introduces corpus poisoning as a new attack…
Randomized Smoothing Meets Vision-Language Models
Emmanouil Seferis, Changshun Wu, Stefanos Kollias +2
Randomized smoothing (RS) is one of the prominent techniques to ensure the correctness of machine learning models, where point-wise robustness certificates can be derived analytica…
Estimating the Robustness Radius for Randomized Smoothing with 100 Sample Efficiency
Emmanouil Seferis, Stefanos Kollias, Chih-Hong Cheng
Randomized smoothing (RS) has successfully been used to improve the robustness of predictions for deep neural networks (DNNs) by adding random noise to create multiple variations o…