17 citations · 53 across the 16 of their papers we have counts for
17 papers
Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations
Hanwei Zhang, Tianma Hu, Gaojie Jin +2
Concept Bottleneck Models (CBMs) are designed to provide interpretable intermediate representations, yet how such bottlenecks affect robustness remains unclear, with existing studi…
NS-ATTENTION: Newton-Schulz Transformations of Attention Outputs in Vision Transformers
Xiaohe Jiang, Guoqiang Zhang, Tianjin Huang +1
Newton-Schulz (NS) iteration has recently been used in the Muon optimizer to transform update matrices during the training of large language models. Motivated by its spectral effec…
Confusion-Aware Spectral Regularizer for Long-Tailed Recognition
Ziquan Zhu, Gaojie Jin, Hanruo Zhu +11
Long-tailed image classification remains a long-standing challenge, as real-world data typically follow highly imbalanced distributions where a few head classes dominate and many t…
POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization
Xinyu Li, Tianjin Huang, Ronghui Mu +2
Recent advances in Chain-of-Thought (CoT) prompting have substantially enhanced the reasoning capabilities of large language models (LLMs), enabling sophisticated problem-solving t…
ThermoRL:Structure-Aware Reinforcement Learning for Protein Mutation Design to Enhance Thermostability
Xiangwen Wang, Gaojie Jin, Xiaowei Huang +1
Designing mutations to optimize protein thermostability remains challenging due to the complex relationship between sequence variations, structural dynamics, and thermostability, o…
Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifiers
Gaojie Jin, Tianjin Huang, Ronghui Mu +1
Recent studies have identified a critical challenge in deep neural networks (DNNs) known as ``robust fairness", where models exhibit significant disparities in robust accuracy acro…
Enhancing Robust Fairness via Confusional Spectral Regularization
Gaojie Jin, Sihao Wu, Jiaxu Liu +2
Recent research has highlighted a critical issue known as ``robust fairness", where robust accuracy varies significantly across different classes, undermining the reliability of de…
Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environments
Gaojie Jin, Ronghui Mu, Xinping Yi +2
The Invariant Risk Minimization (IRM) approach aims to address the challenge of domain generalization by training a feature representation that remains invariant across multiple en…
Safeguarding Large Language Models: A Survey
Yi Dong, Ronghui Mu, Yanghao Zhang +9
In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure t…
Towards Fairness-Aware Adversarial Learning
Yanghao Zhang, Tianle Zhang, Ronghui Mu +2
Although adversarial training (AT) has proven effective in enhancing the model's robustness, the recently revealed issue of fairness in robustness has not been well addressed, i.e.…
Building Guardrails for Large Language Models
Yi Dong, Ronghui Mu, Gaojie Jin +6
As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts…
Reward Certification for Policy Smoothed Reinforcement Learning
Ronghui Mu, Leandro Soriano Marcolino, Tianle Zhang +3
Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks. Recent studies have introduced "smoothed polici…
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation
Xiaowei Huang, Wenjie Ruan, Wei Huang +14
Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many…
Randomized Adversarial Training via Taylor Expansion
Gaojie Jin, Xinping Yi, Dengyu Wu +2
In recent years, there has been an explosion of research into developing more robust deep neural networks against adversarial examples. Adversarial training appears as one of the m…
Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning
Ronghui Mu, Wenjie Ruan, Leandro Soriano Marcolino +2
Cooperative multi-agent reinforcement learning (c-MARL) is widely applied in safety-critical scenarios, thus the analysis of robustness for c-MARL models is profoundly important. H…
3DVerifier: Efficient Robustness Verification for 3D Point Cloud Models
Ronghui Mu, Wenjie Ruan, Leandro S. Marcolino +1
3D point cloud models are widely applied in safety-critical scenes, which delivers an urgent need to obtain more solid proofs to verify the robustness of models. Existing verificat…
Sparse Adversarial Video Attacks with Spatial Transformations
Ronghui Mu, Wenjie Ruan, Leandro Soriano Marcolino +1
In recent years, a significant amount of research efforts concentrated on adversarial attacks on images, while adversarial video attacks have seldom been explored. We propose an ad…