8 citations · 13 across the 5 of their papers we have counts for
6 papers
Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment
Haoming Yang, Ke Ma, Yangbangyan Jiang +6
Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals under a benign context. We id…
Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs
Haoming Yang, Ke Ma, Xiaojun Jia +3
Despite the remarkable performance of Large Language Models (LLMs), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies ofte…
Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain
Gaozheng Pei, Ke Ma, Yingfei Sun +2
The diffusion-based adversarial purification methods attempt to drown adversarial perturbations into a part of isotropic noise through the forward process, and then recover the cle…
Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection
Zhipeng Yu, Qianqian Xu, Yangbangyan Jiang +2
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving the robustn…
Exploring Query Efficient Data Generation towards Data-free Model Stealing in Hard Label Setting
Gaozheng Pei, Shaojie lyu, Ke Ma +3
Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model's structure, parameters, or training da…
Sequential Manipulation Against Rank Aggregation: Theory and Algorithm
Ke Ma, Qianqian Xu, Jinshan Zeng +4
Rank aggregation with pairwise comparisons is widely encountered in sociology, politics, economics, psychology, sports, etc . Given the enormous social impact and the consequent in…