all InfoSec news
Topic: cs.cl
Protecting Your LLMs with Information Bottleneck
4 days, 2 hours ago |
arxiv.org
Towards Building a Robust Toxicity Predictor
1 week, 4 days ago |
arxiv.org
Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs
2 weeks, 1 day ago |
arxiv.org
Goal-guided Generative Prompt Injection Attack on Large Language Models
2 weeks, 1 day ago |
arxiv.org
SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models
2 weeks, 2 days ago |
arxiv.org
Take a Look at it! Rethinking How to Evaluate Language Model Jailbreak
2 weeks, 3 days ago |
arxiv.org
Watermark-based Detection and Attribution of AI-Generated Content
2 weeks, 5 days ago |
arxiv.org
From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
3 weeks, 2 days ago |
arxiv.org
The VoicePrivacy 2024 Challenge Evaluation Plan
3 weeks, 2 days ago |
arxiv.org
Exploring Backdoor Vulnerabilities of Chat Models
3 weeks, 2 days ago |
arxiv.org
Topic-based Watermarks for LLM-Generated Text
3 weeks, 3 days ago |
arxiv.org
Composite Backdoor Attacks Against Large Language Models
3 weeks, 3 days ago |
arxiv.org
Localizing Paragraph Memorization in Language Models
3 weeks, 5 days ago |
arxiv.org
Items published with this topic over the last 90 days.
Latest
Protecting Your LLMs with Information Bottleneck
4 days, 2 hours ago |
arxiv.org
Towards Building a Robust Toxicity Predictor
1 week, 4 days ago |
arxiv.org
Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs
2 weeks, 1 day ago |
arxiv.org
Goal-guided Generative Prompt Injection Attack on Large Language Models
2 weeks, 1 day ago |
arxiv.org
SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models
2 weeks, 2 days ago |
arxiv.org
Take a Look at it! Rethinking How to Evaluate Language Model Jailbreak
2 weeks, 3 days ago |
arxiv.org
Watermark-based Detection and Attribution of AI-Generated Content
2 weeks, 5 days ago |
arxiv.org
From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
3 weeks, 2 days ago |
arxiv.org
The VoicePrivacy 2024 Challenge Evaluation Plan
3 weeks, 2 days ago |
arxiv.org
Exploring Backdoor Vulnerabilities of Chat Models
3 weeks, 2 days ago |
arxiv.org
Topic-based Watermarks for LLM-Generated Text
3 weeks, 3 days ago |
arxiv.org
Composite Backdoor Attacks Against Large Language Models
3 weeks, 3 days ago |
arxiv.org
Localizing Paragraph Memorization in Language Models
3 weeks, 5 days ago |
arxiv.org
Topic trend (last 90 days)
Top (last 7 days)
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Senior InfoSec Manager - Risk and Compliance
@ Federal Reserve System | Remote - Virginia
Security Analyst
@ Fortra | Mexico
Incident Responder
@ Babcock | Chester, GB, CH1 6ER
Vulnerability, Access & Inclusion Lead
@ Monzo | Cardiff, London or Remote (UK)
Information Security Analyst
@ Unissant | MD, USA