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

October 1, 2024

Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective
Yixin Liu, Arielle Carr, Lichao Sun
Adversarial Attack Data Poisoning Attack Perturbation Analysis Weight Perturbation Linear System Solver

September 29, 2024

Adversarial Examples for DNA Classification
Hyunwoo Yoo
Language Model Adversarial Attack Adversarial Example Biological Sequence DNA Sequence Classification
Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology
Son Quoc Tran, Matt Kretchmar
Adversarial Attack Question Answering Extractive Question Answering Training Method
Nonideality-aware training makes memristive networks more robust to adversarial attacks
Dovydas Joksas, Luis Muñoz-González, Emil Lupu, Adnan Mehonic
Neural Network Adversarial Attack Adversarial Robustness Memristive Device
Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises
Anubhooti Jain, Susim Roy, Kwanit Gupta, Mayank Vatsa, Richa Singh
Adversarial Attack Deep Learning Model Adversarial Perturbation Industrial Disturbing Noise Intent Detection Adversarial Noise Kill Chaos Detection Network
MASKDROID: Robust Android Malware Detection with Masked Graph Representations
Jingnan Zheng, Jiaohao Liu, An Zhang, Jun Zeng, Ziqi Yang, Zhenkai Liang, Tat-Seng Chua
Adversarial Attack Adversarial Example Android Malware

September 27, 2024

Enhancing Robustness of Graph Neural Networks through p-Laplacian
Anuj Kumar Sirohi, Subhanu Halder, Kabir Kumar, Sandeep Kumar
Graph Neural Network Adversarial Attack Native Robustness Graph Based Social Network Analysis Robust Graph Neural Network
Read Over the Lines: Attacking LLMs and Toxicity Detection Systems with ASCII Art to Mask Profanity
Sergey Berezin, Reza Farahbakhsh, Noel Crespi
Language Model Adversarial Attack Medical LLM Read V Toxicity Detection Text Shape Vector Font

September 26, 2024

Evaluation of Security of ML-based Watermarking: Copy and Removal Attacks
Vitaliy Kinakh, Brian Pulfer, Yury Belousov, Pierre Fernandez, Teddy Furon, Slava Voloshynovskiy
Adversarial Attack Global Evaluation Security Related Data Provenance Autoencoder Based Deep Watermarking Data Copying
Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimization
Yunpeng Gong, Qingyuan Zeng, Dejun Xu, Zhenzhong Wang, Min Jiang
Adversarial Attack Evolutionary Multitasking Multimodal Attack
Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations
Supriya Manna, Niladri Sett
Natural Language Processing Adversarial Attack Explainable AI Adversarial Vulnerability Faithfulness Test Adversarial Change
Dark Miner: Defend against unsafe generation for text-to-image diffusion models
Zheling Meng, Bo Peng, Xiaochuan Jin, Yue Jiang, Jing Dong, Wei Wang, Tieniu Tan
Adversarial Attack Text to Image Diffusion Model Erasure Method Generative AI Safety
Improving Fast Adversarial Training via Self-Knowledge Guidance
Chengze Jiang, Junkai Wang, Minjing Dong, Jie Gui, Xinli Shi, Yuan Cao, Yuan Yan Tang, James Tin-Yau Kwok
Adversarial Attack Adversarial Training Adversarial Robustness Fast Adversarial Training Self Knowledge Efficiency Robustness
RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking
Yifan Jiang, Kriti Aggarwal, Tanmay Laud, Kashif Munir, Jay Pujara, Subhabrata Mukherjee
Language Model Adversarial Attack Jailbreak Attack Step Attack Query Enhanced Network

Adversarial Attack

Papers

MOREL: Enhancing Adversarial Robustness through Multi-Objective Representation Learning

On Using Certified Training towards Empirical Robustness

Signal Adversarial Examples Generation for Signal Detection Network via White-Box Attack

Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective

Ranking Over Scoring: Towards Reliable and Robust Automated Evaluation of LLM-Generated Medical Explanatory Arguments

Navigating Threats: A Survey of Physical Adversarial Attacks on LiDAR Perception Systems in Autonomous Vehicles

Robust LLM safeguarding via refusal feature adversarial training

Adversarial Examples for DNA Classification

Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology

Nonideality-aware training makes memristive networks more robust to adversarial attacks

Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises

MASKDROID: Robust Android Malware Detection with Masked Graph Representations

Enhancing Robustness of Graph Neural Networks through p-Laplacian

Read Over the Lines: Attacking LLMs and Toxicity Detection Systems with ASCII Art to Mask Profanity

Evaluation of Security of ML-based Watermarking: Copy and Removal Attacks

Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimization

Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations

Dark Miner: Defend against unsafe generation for text-to-image diffusion models

Improving Fast Adversarial Training via Self-Knowledge Guidance

RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking