Adversarial Defense
10개 벤치마크 · 논문 438편 · 이 태스크의 논문 보기 →
Benchmarks
CIFAR-10
ImageNet
CIFAR-100
MNIST
CAAD 2018
TrojAI Round 0
TrojAI Round 1
miniImageNet
Most implemented
Towards Deep Learning Models Resistant to Adversarial Attacks
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
Certified Adversarial Robustness via Randomized Smoothing
The Limitations of Deep Learning in Adversarial Settings
Theoretically Principled Trade-off between Robustness and Accuracy
Papers
Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivity
Multi-norm adversarial defense aims to protect neural networks against perturbations defined by different norm constraints, but existing methods typically optimize competing robustness objectives within a single paramete…
Adversarial DefenseLarge Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies
Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic, Google, Meta, Microsoft, Stability AI, respectively, are revolutioni…
Adversarial DefenseFederated LearningAnomaly DetectionCode GenerationFleet: Few Shots Lead Effective AI-generated Image Detection
AI-generated image (AIGI) detection is undergoing a critical transition from laboratory benchmarks to open-world adversarial defense. The prevalent paradigm focuses on finding static feature spaces, assuming that some in…
Zero-shot GeneralizationAdversarial DefenseSemantic Smoothing via Novel View Synthesis for Robust SAR Image Classification
Deep neural networks are vulnerable to adversarial perturbations, limiting deployment in safety-critical applications such as synthetic aperture radar (SAR) automatic target recognition (ATR). Randomized smoothing improv…
Novel View SynthesisImage ClassificationAdversarial DefenseGuaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we p…
Adversarial DefenseEnhancing Adversarial Robustness in Network Intrusion Detection: A Layer-wise Adaptive Regularization Approach
The new wave of adversarial attacks that utilize gradient-related vulnerabilities in neural network-based classifiers makes Network Intrusion Detection Systems more open to such threats. Although state-of-the-art adversa…
Network Intrusion DetectionAdversarial RobustnessAdversarial Defense