Targeted Attacks and Defenses for Distributed Federated Learning in Vehicular Networks
"攻击防御" 相关文章
Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
Cross-Modal Content Optimization for Steering Web Agent Preferences
ToolTweak: An Attack on Tool Selection in LLM-based Agents
Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization
Game-Theoretic Resilience Framework for Cyber-Physical Microgrids using Multi-Agent Reinforcement Learning
CopyrightShield: Enhancing Diffusion Model Security against Copyright Infringement Attacks
Deciphering the Interplay between Attack and Protection Complexity in Privacy-Preserving Federated Learning
Attacks and Defenses Against LLM Fingerprinting
ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments
FLAT: Latent-Driven Arbitrary-Target Backdoor Attacks in Federated Learning
PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detection
Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks
Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method
Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligence
Backdooring Bias (B^2) into Stable Diffusion Models
「推安早报」1017 | 域安全、红蓝工具节选
Deepening Safety Alignment in Large Language Models (LLMs)
