会员服务
FSLH: Flexible Mechanized Speculative Load Hardening
Arxiv
0+阅读 · 1月6日
When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents
Arxiv
0+阅读 · 1月6日
Steerability of Instrumental-Convergence Tendencies in LLMs
Arxiv
0+阅读 · 1月6日
A Decade-long Landscape of Advanced Persistent Threats: Longitudinal Analysis and Global Trends
Arxiv
0+阅读 · 1月6日
Hidden State Poisoning Attacks against Mamba-based Language Models
Arxiv
0+阅读 · 1月6日
Selfish Mining in Multi-Attacker Scenarios: An Empirical Evaluation of Nakamoto, Fruitchain, and Strongchain
Arxiv
0+阅读 · 1月6日
VFEFL: Privacy-Preserving Federated Learning against Malicious Clients via Verifiable Functional Encryption
Arxiv
0+阅读 · 1月6日
JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification
Arxiv
0+阅读 · 1月6日
E$^2$AT: Multimodal Jailbreak Defense via Dynamic Joint Optimization for Multimodal Large Language Models
Arxiv
0+阅读 · 1月6日
VocalBridge: Latent Diffusion-Bridge Purification for Defeating Perturbation-Based Voiceprint Defenses
Arxiv
0+阅读 · 1月5日
Window-based Membership Inference Attacks Against Fine-tuned Large Language Models
Arxiv
0+阅读 · 1月6日
Training Set Reconstruction from Differentially Private Forests: How Effective is DP?
Arxiv
0+阅读 · 1月5日
Coordinated Multi-Domain Deception: A Stackelberg Game Approach
Arxiv
0+阅读 · 1月5日
Quality Degradation Attack in Synthetic Data
Arxiv
0+阅读 · 1月6日
Cyber Security of Sensor Systems for State Sequence Estimation: an AI Approach
Arxiv
0+阅读 · 1月6日
参考链接
微信扫码咨询专知VIP会员
Top