Gradient Based Adversarial

Gradient-based adversarial attacks exploit the vulnerabilities of machine learning models by generating subtly perturbed inputs that cause misclassification. Current research focuses on improving the efficiency and effectiveness of these attacks across various model architectures, including large language models, graph neural networks, and image classifiers, often leveraging techniques like gradient estimation and optimization algorithms such as projected gradient descent and momentum iterative FGSM. This research is crucial for enhancing the robustness and security of machine learning systems in diverse applications, ranging from image recognition and natural language processing to critical infrastructure and cybersecurity. Understanding and mitigating these attacks is vital for ensuring the reliability and trustworthiness of AI systems.

Papers

November 7, 2024

Adversarial Robustness of In-Context Learning in Transformers for Linear Regression
Usman Anwar, Johannes Von Oswald, Louis Kirsch, David Krueger, Spencer Frei
Transformer Megatron Decepticons Context Learning Adversarial Training Adversarial Robustness Novel Regression Layer Transformer Linear Ordered Data Transformer Based Generative Adversarial Gradient Based Adversarial

October 29, 2024

Enhancing Adversarial Attacks through Chain of Thought
Jingbo Su
Large Language Model Adversarial Attack Side Chain Thought Reasoning Gradient Based Adversarial

October 17, 2024

MMAD-Purify: A Precision-Optimized Framework for Efficient and Scalable Multi-Modal Attacks
Xinxin Liu, Zhongliang Guo, Siyuan Huang, Chun Pong Lau
Diffusion Model Adversarial Attack Adversarial Example Adversarial Perturbation Gradient Based Adversarial Multimodal Attack

September 11, 2024

Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks
Md Zarif Hossain, Ahmed Imteaj
Adversarial Attack Vision Language Model Large Vision Language Model Jailbreak Attack Adversarial Manipulation CLIP Vision Encoder Gradient Based Adversarial Robust Encoders

August 22, 2024

Leveraging Information Consistency in Frequency and Spatial Domain for Adversarial Attacks
Zhibo Jin, Jiayu Zhang, Zhiyu Zhu, Xinyi Wang, Yiyun Huang, Huaming Chen
Adversarial Attack Adversarial Example High Frequency Spatial Domain Gradient Based Adversarial Spectral Domain Attack

May 25, 2024

Detecting Adversarial Data via Perturbation Forgery
Qian Wang, Chen Li, Yuchen Luo, Hefei Ling, Ping Li, Jiazhong Chen, Shijuan Huang, Ning Yu
Adversarial Attack Adversarial Noise Adversarial Detection Adversarial Data Gradient Based Adversarial Specific Forgery

October 23, 2023

AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
Sicheng Zhu, Ruiyi Zhang, Bang An, Gang Wu, Joe Barrow, Zichao Wang, Furong Huang, Ani Nenkova, Tong Sun
Adversarial Attack Jailbreak Attack Attack Success Rate Gradient Based Adversarial

May 4, 2023

Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning
Dayuan Chen, Jian Zhang, Yuqian Lv, Jinhuan Wang, Hongjie Ni, Shanqing Yu, Zhen Wang, Qi Xuan
Reinforcement Learning Graph Neural Network Gradient Based Adversarial Node Injection Label Attack Graph Injection Attack

January 27, 2023

Adapting Step-size: A Unified Perspective to Analyze and Improve Gradient-based Methods for Adversarial Attacks
Wei Tao, Lei Bao, Sheng Long, Gaowei Wu, Qing Tao
Adversarial Attack Adversarial Example NCD Method Gradient Method Unified View Step Size Gradient Based Adversarial Adaptive Gradient

August 18, 2022

Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance
Bahjat Kawar, Roy Ganz, Michael Elad
Generative Model Image Synthesis Generative Diffusion Model Denoising Diffusion Robust Classifier Gradient Based Adversarial Classifier Guidance

August 1, 2022

Attacking Adversarial Defences by Smoothing the Loss Landscape
Panagiotis Eustratiadis, Henry Gouk, Da Li, Timothy Hospedales
Adversarial Attack Loss Landscape Adversarial DEfense Gradient Based Adversarial Gradient Obfuscation

June 14, 2022

Downlink Power Allocation in Massive MIMO via Deep Learning: Adversarial Attacks and Training
B. R. Manoj, Meysam Sadeghi, Erik G. Larsson
Deep Learning Adversarial Attack Training Data Adversarial Training Adversarial Perturbation Adversarial Scenario Massive MIMO Gradient Based Adversarial

May 19, 2022

Focused Adversarial Attacks
Thomas Cilloni, Charles Walter, Charles Fleming
Adversarial Attack Adversarial Example Adversarial Method Gradient Based Attack Gradient Based Adversarial

April 22, 2022

How Sampling Impacts the Robustness of Stochastic Neural Networks
Sina Däubener, Asja Fischer
Native Robustness Adversarial Example Model Robustness Stochastic Neural Network Gradient Based Adversarial

March 11, 2022

Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers
Sahar Sadrizadeh, Ljiljana Dolamic, Pascal Frossard
Adversarial Attack Adversarial Example Transformer Based Adversarial Perturbation Gradient Based Adversarial Sparse Adversarial Attack

February 2, 2022

Speaker Normalization for Self-supervised Speech Emotion Recognition
Itai Gat, Hagai Aronowitz, Weizhong Zhu, Edmilson Morais, Ron Hoory
Speech Emotion Recognition Speech Emotion Gradient Based Adversarial Speaker Normalization

January 20, 2022

Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation
Sixiao Zhang, Hongxu Chen, Xiangguo Sun, Yicong Li, Guandong Xu
Contrastive Learning Adversarial Attack Graph Representation Learning Supervised Contrastive Loss Gradient Based Adversarial Graph Poisoning Attack

December 28, 2021

A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs
Han Lu, Zenan Li, Runzhong Wang, Qibing Ren, Junchi Yan, Xiaokang Yang
Native Robustness Graph Drawing General Framework Hybrid Solver Gradient Based Adversarial Combinatorial Optimization Solver

December 10, 2021

RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit
Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe
Adversarial Attack Adversarial Example Decision Based Gradient Based Adversarial Blackbox Attack