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
REGE: A Method for Incorporating Uncertainty in Graph Embeddings
Zohair Shafi, Germans Savcisens, Tina Eliassi-Rad
Nearly Solved? Robust Deepfake Detection Requires More than Visual Forensics
Guy Levy, Nathan Liebmann
From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation
Kristoffer Wickstrøm, Marina Marie-Claire Höhne, Anna Hedström
Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation
Xuying Li, Zhuo Li, Yuji Kosuga, Yasuhiro Yoshida, Victor Bian
On the Lack of Robustness of Binary Function Similarity Systems
Gianluca Capozzi, Tong Tang, Jie Wan, Ziqi Yang, Daniele Cono D'Elia, Giuseppe Antonio Di Luna, Lorenzo Cavallaro, Leonardo Querzoni
Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial Attacks
Dario Serez, Marco Cristani, Alessio Del Bue, Vittorio Murino, Pietro Morerio
Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?
Sravanti Addepalli, Yerram Varun, Arun Suggala, Karthikeyan Shanmugam, Prateek Jain
Testing Neural Network Verifiers: A Soundness Benchmark with Hidden Counterexamples
Xingjian Zhou, Hongji Xu, Andy Xu, Zhouxing Shi, Cho-Jui Hsieh, Huan Zhang
Out-of-Distribution Detection for Neurosymbolic Autonomous Cyber Agents
Ankita Samaddar, Nicholas Potteiger, Xenofon Koutsoukos
Gaussian Splatting Under Attack: Investigating Adversarial Noise in 3D Objects
Abdurrahman Zeybey, Mehmet Ergezer, Tommy Nguyen
Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks
Zijiao Yang, Xiangxi Shi, Eric Slyman, Stefan Lee
Defending Against Diverse Attacks in Federated Learning Through Consensus-Based Bi-Level Optimization
Nicolás García Trillos, Aditya Kumar Akash, Sixu Li, Konstantin Riedl, Yuhua Zhu
Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language Model
Xi Cao, Nuo Qun, Quzong Gesang, Yulei Zhu, Trashi Nyima