481 citations · 997 across the 45 of their papers we have counts for
47 papers
DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models
Xuyang Zhong, Qizhang Li, Yiwen Guo +1
We propose DualOptim+, a novel optimization framework for improving machine unlearning in large language models. It introduces a base state to capture common representations shared…
Improved Generation of Adversarial Examples Against Safety-aligned LLMs
Qizhang Li, Yiwen Guo, Wangmeng Zuo +1
Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due…
LLM as a Complementary Optimizer to Gradient Descent: A Case Study in Prompt Tuning
Zixian Guo, Ming Liu, Zhilong Ji +3
Mastering a skill generally relies on both hands-on experience from doers and insightful, high-level guidance by mentors. Will this strategy also work well for solving complex non-…
Intrusion Detection at Scale with the Assistance of a Command-line Language Model
Jiongliang Lin, Yiwen Guo, Hao Chen
Intrusion detection is a long standing and crucial problem in security. A system capable of detecting intrusions automatically is on great demand in enterprise security solutions.…
UniTSyn: A Large-Scale Dataset Capable of Enhancing the Prowess of Large Language Models for Program Testing
Yifeng He, Jiabo Huang, Yuyang Rong +3
The remarkable capability of large language models (LLMs) in generating high-quality code has drawn increasing attention in the software testing community. However, existing code L…
Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation
Zixian Guo, Yuxiang Wei, Ming Liu +4
Parameter-efficient fine-tuning (PEFT) methods have provided an effective way for adapting large vision-language models to specific tasks or scenarios. Typically, they learn a very…
FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models
Wan Xu, Tianyu Huang, Tianyu Qu +3
Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. However, many of these works l…
Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly
Qizhang Li, Yiwen Guo, Wangmeng Zuo +1
The adversarial vulnerability of deep neural networks (DNNs) has drawn great attention due to the security risk of applying these models in real-world applications. Based on transf…
Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning
Qing Miao, Xiaohe Wu, Chao Xu +4
Learning with noisy labels (LNL) has been extensively studied, with existing approaches typically following a framework that alternates between clean sample selection and semi-supe…
DualAug: Exploiting Additional Heavy Augmentation with OOD Data Rejection
Zehao Wang, Yiwen Guo, Qizhang Li +2
Data augmentation is a dominant method for reducing model overfitting and improving generalization. Most existing data augmentation methods tend to find a compromise in augmenting…
The Program Testing Ability of Large Language Models for Code
Weimin Xiong, Yiwen Guo, Hao Chen
Recent development of large language models (LLMs) for code like CodeX and CodeT5+ demonstrates tremendous promise in achieving code intelligence. Their ability of synthesizing cod…
Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection
Yuanze Li, Haolin Wang, Shihao Yuan +6
Due to the training configuration, traditional industrial anomaly detection (IAD) methods have to train a specific model for each deployment scenario, which is insufficient to meet…
Adversarial Examples Are Not Real Features
Ang Li, Yifei Wang, Yiwen Guo +1
The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerabili…
Code Representation Pre-training with Complements from Program Executions
Jiabo Huang, Jianyu Zhao, Yuyang Rong +3
Large language models (LLMs) for natural language processing have been grafted onto programming language modeling for advancing code intelligence. Although it can be represented in…
Ref-Diff: Zero-shot Referring Image Segmentation with Generative Models
Minheng Ni, Yabo Zhang, Kailai Feng +3
Zero-shot referring image segmentation is a challenging task because it aims to find an instance segmentation mask based on the given referring descriptions, without training on th…
Improving Transferability of Adversarial Examples via Bayesian Attacks
Qizhang Li, Yiwen Guo, Xiaochen Yang +2
The transferability of adversarial examples allows for the attack on unknown deep neural networks (DNNs), posing a serious threat to many applications and attracting great attentio…
Understanding Programs by Exploiting (Fuzzing) Test Cases
Jianyu Zhao, Yuyang Rong, Yiwen Guo +2
Semantic understanding of programs has attracted great attention in the community. Inspired by recent successes of large language models (LLMs) in natural language understanding, t…
Improving Adversarial Transferability via Intermediate-level Perturbation Decay
Qizhang Li, Yiwen Guo, Wangmeng Zuo +1
Intermediate-level attacks that attempt to perturb feature representations following an adversarial direction drastically have shown favorable performance in crafting transferable…
CFA: Class-wise Calibrated Fair Adversarial Training
Zeming Wei, Yifei Wang, Yiwen Guo +1
Adversarial training has been widely acknowledged as the most effective method to improve the adversarial robustness against adversarial examples for Deep Neural Networks (DNNs). S…
Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples
Qizhang Li, Yiwen Guo, Wangmeng Zuo +1
The transferability of adversarial examples across deep neural networks (DNNs) is the crux of many black-box attacks. Many prior efforts have been devoted to improving the transfer…
Texts as Images in Prompt Tuning for Multi-Label Image Recognition
Zixian Guo, Bowen Dong, Zhilong Ji +3
Prompt tuning has been employed as an efficient way to adapt large vision-language pre-trained models (e.g. CLIP) to various downstream tasks in data-limited or label-limited setti…
When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture
Yichuan Mo, Dongxian Wu, Yifei Wang +2
Vision Transformers (ViTs) have recently achieved competitive performance in broad vision tasks. Unfortunately, on popular threat models, naturally trained ViTs are shown to provid…
Squeeze Training for Adversarial Robustness
Qizhang Li, Yiwen Guo, Wangmeng Zuo +1
The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community. The problem is related to non-flatness and…
On Steering Multi-Annotations per Sample for Multi-Task Learning
Yuanze Li, Yiwen Guo, Qizhang Li +2
The study of multi-task learning has drawn great attention from the community. Despite the remarkable progress, the challenge of optimally learning different tasks simultaneously r…