Feeds to Scour
SubscribedAll
Scoured 187234 posts in 69.8 ms
Semantic Denial of Service in LLM-controlled robots  💉Prompt Injection
arxiv.org·1d
Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models  🕳LLM Vulnerabilities
arxiv.org·6d
RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents  💉Prompt Injection
arxiv.org·2d
SMSI: System Model Security Inference: Automated Threat Modeling for Cyber-Physical Systems  🛡️AI Safety
arxiv.org·2d
Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective  🛡️AI Safety
arxiv.org·3d
AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization  💉Prompt Injection
arxiv.org·2d
Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents  🕳LLM Vulnerabilities
arxiv.org·2d
Adaptive Prompt Embedding Optimization for LLM Jailbreaking  💉Prompt Injection
arxiv.org·1d
Poisoning Learned Index Structures: Static and Dynamic Adversarial Attacks on ALEX  📚Index Structures
arxiv.org·1d
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents  💉Prompt Injection
arxiv.org·1d
Training a General Purpose Automated Red Teaming Model  🎰Bandit Algorithms
arxiv.org·2d
UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems  🛡️AI Safety
arxiv.org·2d

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