会员服务
GNSS Spoofing Threat for V2X communications
Arxiv
0+阅读 · 6月18日
Efficient Document Tampering Localization with Multi-Level Discrepancy Features and Unified DCT-Quantization Embedding
Arxiv
0+阅读 · 6月21日
Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems
Arxiv
0+阅读 · 6月16日
CRAFT: Fine-Grained Cost-Aware Expert Replication For Efficient Mixture-of-Experts Serving
Arxiv
0+阅读 · 5月29日
CRAFT: Coaching Reinforcement Learning Autonomously using Foundation Models for Multi-Robot Coordination Tasks
Arxiv
0+阅读 · 6月5日
Crafting Reversible SFT Behaviors in Large Language Models
Arxiv
0+阅读 · 5月7日
TombWriter: Scaffolding Story Archeology through Beat-Level Interaction in Human-AI Co-Writing
Arxiv
0+阅读 · 5月19日
Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction
Arxiv
0+阅读 · 5月18日
Re-Triggering Safeguards within LLMs for Jailbreak Detection
Arxiv
0+阅读 · 5月11日
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
Arxiv
0+阅读 · 5月19日
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails
Arxiv
0+阅读 · 6月12日
Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
Arxiv
0+阅读 · 6月1日
Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
Arxiv
0+阅读 · 5月29日
KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware
Arxiv
0+阅读 · 5月29日
SwitchPatch: Physical Adversarial Attack Strategy with Switchable Adversarial Objectives
Arxiv
0+阅读 · 5月18日
参考链接
微信扫码咨询专知VIP会员
Top