Feeds to Scour
SubscribedAll
Scoured 187609 posts in 19.8 ms
The Agentic AI Security Company  🔧Agent Tooling
straiker.ai·5d·Hacker News
A grand jury indicted Orleans Parish Sheriff Susan Hutson over a 2025 jailbreak involving 10 inmates. https://www.fox13seattle.com/news/new-orleans-sheriff-susa...  🔍OSINT
twitter.macworks.dev
·2d
(The Voice) Multilingual Layer  📦Software Supply Chain
1688.pixel-geist.co.za·5d·DEV
SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts  🕳LLM Vulnerabilities
arxiv.org·2d
Sheriff Susan Hutson charged in 30-count indictment in connection with Louisiana jailbreak  🕳LLM Vulnerabilities
ketv.com·2d
Jailbreaking a robot vacuum to run Tailscale and Valetudo  🔌Embedded Systems
tailscale.com·6d·Hacker News
One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety  🤖LLM
arxiv.org·2d
Nosebleed  🪝eBPF
kindlemodding.org·5d
New Orleans sheriff indicted after 'poor management' led to infamous toilet jailbreak  🕳LLM Vulnerabilities
local12.com·1d
Activist defends ‘crustacean jailbreak’ after throwing restaurant’s pet crayfish into the ocean  🤖Web Crawling Politeness
the-independent.com·4d
Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection  🛡️AI Security
arxiv.org·1d
Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry  🛡️AI Security
arxiv.org·1d
Evaluation of Prompt Injection Defenses in Large Language Models  🛡️AI Security
arxiv.org·4d
Adaptive Prompt Embedding Optimization for LLM Jailbreaking  🪄Prompt Engineering
arxiv.org·3d
RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents  🕳LLM Vulnerabilities
arxiv.org·4d
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents  🕷️Web Crawling
arxiv.org·3d
Mechanistic Steering of LLMs Reveals Layer-wise Feature Vulnerabilities in Adversarial Settings  🛡️AI Security
arxiv.org·4d
Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents  🛡️AI Security
arxiv.org·4d
From Stateless Queries to Autonomous Actions: A Layered Security Framework for Agentic AI Systems  🛡️AI Security
arxiv.org·4d
Cross-Lingual Jailbreak Detection via Semantic Codebooks  🔐Hardware Security
arxiv.org·3d

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help