Adversarial Attack

Adversarial attacks aim to deceive machine learning models by subtly altering input data, causing misclassifications or other erroneous outputs. Current research focuses on developing more robust models and detection methods, exploring various attack strategies across different model architectures (including vision transformers, recurrent neural networks, and graph neural networks) and data types (images, text, signals, and tabular data). Understanding and mitigating these attacks is crucial for ensuring the reliability and security of AI systems in diverse applications, from autonomous vehicles to medical diagnosis and cybersecurity.

Papers

May 12, 2024

VALID: a Validated Algorithm for Learning in Decentralized Networks with Possible Adversarial Presence
Mayank Bakshi, Sara Ghasvarianjahromi, Yauhen Yakimenka, Allison Beemer, Oliver Kosut, Joerg Kliewer
LeArning Abstract Adversarial Attack Decentralized Learning Concurrent Validity Decentralized Network

May 10, 2024

Disttack: Graph Adversarial Attacks Toward Distributed GNN Training
Yuxiang Zhang, Xin Liu, Meng Wu, Wei Yan, Mingyu Yan, Xiaochun Ye, Dongrui Fan
Graph Neural Network Adversarial Attack Gene Level GNN GNN Training Graph Adversarial Attack

May 8, 2024

Untargeted Adversarial Attack on Knowledge Graph Embeddings
Tianzhe Zhao, Jiaoyan Chen, Yanchi Ru, Qika Lin, Yuxia Geng, Jun Liu
Adversarial Attack Knowledge Graph Knowledge Graph Embeddings Knowledge Graph Representation Learning Untargeted Adversarial Attack

May 7, 2024

Revisiting Character-level Adversarial Attacks for Language Models
Elias Abad Rocamora, Yongtao Wu, Fanghui Liu, Grigorios G. Chrysos, Volkan Cevher
Adversarial Attack Adversarial Example Token Level Attack

May 6, 2024

May 5, 2024

You Only Need Half: Boosting Data Augmentation by Using Partial Content
Juntao Hu, Yuan Wu
Adversarial Attack Data Augmentation Data Augmentation Technique Novel Data Augmentation Data Augmentation Strategy Image Data Augmentation Missing Half

May 4, 2024

Assessing Adversarial Robustness of Large Language Models: An Empirical Study
Zeyu Yang, Zhao Meng, Xiaochen Zheng, Roger Wattenhofer
Adversarial Attack Adversarial Robustness Adversarial Perturbation Empirical Study White Box LLM Robustness

May 3, 2024

May 2, 2024

Boosting Jailbreak Attack with Momentum
Yihao Zhang, Zeming Wei
Adversarial Attack Jailbreak Attack Adversarial Prompt Residual Momentum Gradient Based Attack

May 1, 2024

Adversarial Attacks and Defense for Conversation Entailment Task
Zhenning Yang, Ryan Krawec, Liang-Yuan Wu
Large Language Model Adversarial Attack Textual Entailment Fast Adversarial Training Monotone Adversary

April 30, 2024

Adversarial Attack

Papers

VALID: a Validated Algorithm for Learning in Decentralized Networks with Possible Adversarial Presence

Disttack: Graph Adversarial Attacks Toward Distributed GNN Training

Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Models

BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimization

Towards Accurate and Robust Architectures via Neural Architecture Search

Untargeted Adversarial Attack on Knowledge Graph Embeddings

Revisiting Character-level Adversarial Attacks for Language Models

Enhancing O-RAN Security: Evasion Attacks and Robust Defenses for Graph Reinforcement Learning-based Connection Management

Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferability

To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models

You Only Need Half: Boosting Data Augmentation by Using Partial Content

Assessing Adversarial Robustness of Large Language Models: An Empirical Study

Adversarial Botometer: Adversarial Analysis for Social Bot Detection

From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings

Impact of Architectural Modifications on Deep Learning Adversarial Robustness

A Novel Approach to Guard from Adversarial Attacks using Stable Diffusion

Boosting Jailbreak Attack with Momentum

Adversarial Attacks and Defense for Conversation Entailment Task

Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective

Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective