Feeds to Scour
SubscribedAll
Scoured 7129 posts in 40.8 ms
SafeRedirect: Defeating Internal Safety Collapse via Task-Completion Redirection in Frontier LLMs  🪄Prompt Engineering
arxiv.org·6d
CSC: Turning the Adversary's Poison against Itself  🔐Cryptography
arxiv.org·6d
Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets  🛡️AI Security
arxiv.org·3d
PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training  🕳LLM Vulnerabilities
arxiv.org·3d
Recognition Without Authorization: LLMs and the Moral Order of Online Advice  🪄Prompt Engineering
arxiv.org·3d
Rethinking Publication: A Certification Framework for AI-Enabled Research  🛡️AI Safety
arxiv.org·3d
Institutionalizing Best Practices in Research Computing: A Framework and Case Study for Improving User Onboarding  👥UX Research
arxiv.org·6d
Quantifying Interface Procedure Coupling Risks in Digital Nuclear Control Rooms: An Event Based Human Reliability Assessment  🛡️AI Safety
arxiv.org·3d
How Large Language Models Balance Internal Knowledge with User and Document Assertions  🤖LLM
arxiv.org·3d
Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs  ✅Formal Verification
arxiv.org·6d
Taste for Privacy: How Context, Identity, and Lived-Experience Shape Information Sharing Preferences  👥UX Research
arxiv.org·3d
Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study  🕳LLM Vulnerabilities
arxiv.org·6d

No more posts from hop1.ng.1357's subscribed feeds.

Scour all 24433 feedsLearn more about Feeds

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