Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss
"对抗攻击" 相关文章
RCR-AF: Enhancing Model Generalization via Rademacher Complexity Reduction Activation Function
智能体安全与可信AI：防护机制与伦理考量
Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments
Evaluating the Performance of AI Text Detectors, Few-Shot and Chain-of-Thought Prompting Using DeepSeek Generated Text
From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models
Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach
VTarbel: Targeted Label Attack with Minimal Knowledge on Detector-enhanced Vertical Federated Learning
Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack
Scaling Decentralized Learning with FLock
Non-Adaptive Adversarial Face Generation
Crafting Imperceptible On-Manifold Adversarial Attacks for Tabular Data
False Alarms, Real Damage: Adversarial Attacks Using LLM-based Models on Text-based Cyber Threat Intelligence Systems
DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective
Evaluating the Evaluators: Trust in Adversarial Robustness Tests
Concept-based Adversarial Attack: a Probabilistic Perspective
Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States
Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation
Vulnerability in Trusted Monitoring and Mitigations
深度研究 | Agentic AI系统安全防护实施指南
