Attack Framework

Attack frameworks encompass the design and implementation of methods to probe vulnerabilities in various machine learning models and systems, aiming to assess their robustness and identify weaknesses. Current research focuses on developing sophisticated attacks against large language models (LLMs), recommender systems, and image generation models, often employing techniques like adversarial training, generative adversarial networks (GANs), reinforcement learning, and evolutionary strategies to create effective and evasive attacks. These frameworks are crucial for evaluating the security and safety of increasingly prevalent AI systems, informing the development of more robust and reliable models and ultimately contributing to the responsible deployment of AI technologies.

Papers

September 23, 2024

Effective and Evasive Fuzz Testing-Driven Jailbreaking Attacks against LLMs
Xueluan Gong, Mingzhe Li, Yilin Zhang, Fengyuan Ran, Chen Chen, Yanjiao Chen, Qian Wang, Kwok-Yan Lam
Large Language Model Jailbreak Attack New Attack Attack Framework Adaptive Mutation

May 20, 2024

EGAN: Evolutional GAN for Ransomware Evasion
Daniel Commey, Benjamin Appiah, Bill K. Frimpong, Isaac Osei, Ebenezer N. A. Hammond, Garth V. Crosby
Adversarial Malware Attack Framework Ransomware Attack Modeling Technique Semantic Evolution GAN

April 24, 2024

Attacks on Third-Party APIs of Large Language Models
Wanru Zhao, Vidit Khazanchi, Haodi Xing, Xuanli He, Qiongkai Xu, Nicholas Donald Lane
New Attack API Usage Real World Attack Attack Framework

April 23, 2024

Talk Too Much: Poisoning Large Language Models under Token Limit
Jiaming He, Wenbo Jiang, Guanyu Hou, Wenshu Fan, Rui Zhang, Hongwei Li
Poisoning Attack Attack Framework

April 2, 2024

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
Jiachen Ma, Anda Cao, Zhiqing Xiao, Yijiang Li, Jie Zhang, Chao Ye, Junbo Zhao
Diffusion Model Jailbreak Attack Attack Framework Online Safety Verification Safety Attack

February 28, 2024

Living-off-The-Land Reverse-Shell Detection by Informed Data Augmentation
Dmitrijs Trizna, Luca Demetrio, Battista Biggio, Fabio Roli
Data Augmentation Threat Intelligence Rural Connectivity Attack Framework

February 14, 2024

Review-Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems
Shiyi Yang, Lina Yao, Chen Wang, Xiwei Xu, Liming Zhu
Recommender System Novel Attack Attack Framework Attack Efficacy

November 29, 2023

VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models
Xiang Li, Qianli Shen, Kenji Kawaguchi
Generative Model Copyright Protection Text to Image Generative Model Attack Framework Enhancement Attack

November 20, 2023

Evil Geniuses: Delving into the Safety of LLM-based Agents
Yu Tian, Xiao Yang, Jingyuan Zhang, Yinpeng Dong, Hang Su
Large Language Model Human SAFETY LLM Based Agent Attack Framework

September 12, 2023

Generalized Attacks on Face Verification Systems
Ehsan Nazari, Paula Branco, Guy-Vincent Jourdan
Adversarial Attack Face Verification Evasion Attack Attack Framework

June 5, 2023

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
Kostadin Garov, Dimitar I. Dimitrov, Nikola Jovanović, Martin Vechev
Secure Aggregation Accurate Decoding Plain Sight Attack Framework Client Side

April 5, 2023

A Certified Radius-Guided Attack Framework to Image Segmentation Models
Wenjie Qu, Youqi Li, Binghui Wang
Adversarial Perturbation White Box Image Segmentation Model Attack Framework Projected Gradient Descent Attack

March 6, 2023

Learning to Backdoor Federated Learning
Henger Li, Chen Wu, Sencun Zhu, Zizhan Zheng
LeArning Abstract Federated Learning Backdoor Attack Backdoor Learning Attack Performance Attack Framework Aggregation Defense

December 5, 2022

Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning
Marissa Connor, Vincent Emanuele
Semi Supervised Learning Semi Supervised Context Information Poisoning Attack Data Poisoning Attack Backdoor Poisoning Attack Attack Framework

August 26, 2022

ATTRITION: Attacking Static Hardware Trojan Detection Techniques Using Reinforcement Learning
Vasudev Gohil, Hao Guo, Satwik Patnaik, Jeyavijayan, Rajendran
Reinforcement Learning Attack Success Rate Hardware Trojan Attack Framework Hardware Trojan Detection Employee Attrition

July 8, 2022

Online Evasion Attacks on Recurrent Models:The Power of Hallucinating the Future
Byunggill Joe, Insik Shin, Jihun Hamm
Real Power Future Reasoning Content Hallucination White Box Evasion Attack Adversarial Objective Attack Framework

May 2, 2022

Deep-Attack over the Deep Reinforcement Learning
Yang Li, Quan Pan, Erik Cambria
Adversarial Attack Deep Reinforcement Learning Adversarial Training Attack Framework Attack Model Deep Attack

April 10, 2022

Measuring the False Sense of Security
Carlos Gomes
Natural Gradient Security Related Adversarial DEfense False Sense Attack Framework Gradient Masking