会员服务
PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks
Arxiv
0+阅读 · 10月23日
CRAFT: Characterizing and Root-Causing Fault Injection Threats at Pre-Silicon
Arxiv
0+阅读 · 10月22日
Are Modern Speech Enhancement Systems Vulnerable to Adversarial Attacks?
Arxiv
0+阅读 · 10月22日
Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1
Arxiv
0+阅读 · 10月22日
LENS: Large Pre-trained Transformer for Exploring Financial Time Series Regularities
Arxiv
0+阅读 · 10月21日
BreakFun: Jailbreaking LLMs via Schema Exploitation
Arxiv
0+阅读 · 10月19日
Optimistic Reinforcement Learning-Based Skill Insertions for Task and Motion Planning
Arxiv
0+阅读 · 10月15日
When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers
Arxiv
0+阅读 · 10月14日
MS-GAGA: Metric-Selective Guided Adversarial Generation Attack
Arxiv
0+阅读 · 10月14日
Patentformer: A demonstration of AI-assisted automated patent drafting
Arxiv
0+阅读 · 10月10日
GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis
Arxiv
0+阅读 · 10月10日
DeHate: A Stable Diffusion-based Multimodal Approach to Mitigate Hate Speech in Images
Arxiv
0+阅读 · 10月10日
Differential Analysis of Pseudo Haptic Feedback: Novel Comparative Study of Visual and Auditory Cue Integration for Psychophysical Evaluation
Differential Analysis of Pseudo Haptic Feedback: Novel Comparative Study of Visual and Auditory Cue Integration for Psychophysical Evaluation
Arxiv
0+阅读 · 10月10日
LacAIDes: Generative AI-Supported Creative Interactive Circuits Crafting to Enliven Traditional Lacquerware
Arxiv
0+阅读 · 10月9日
Tailoring materials into kirigami robots
Arxiv
0+阅读 · 10月8日
参考链接
微信扫码咨询专知VIP会员
Top