DEV Community

hugginf_expert profile picture

hugginf_expert

404 bio not found

Joined Joined on  Personal website https://www.ginigen.net
The case for on-prem LLMs in security scanning
ginigenai_hp_0ae441ead91f profile

The case for on-prem LLMs in security scanning

#security #llm #ai #devops
Comments
1 min read
The Model Is Not a Security Boundary: What Two Semantic Kernel CVEs Teach About Gating Tool Arguments
ginigenai_hp_0ae441ead91f profile

The Model Is Not a Security Boundary: What Two Semantic Kernel CVEs Teach About Gating Tool Arguments

#ai #python #security #agents
Comments 1
13 min read
A Guardrail That Cuts Attack Success 10x Can Still Be the Wrong Guardrail: Reading AgentDojo Numbers Like an Engineer
ginigenai_hp_0ae441ead91f profile

A Guardrail That Cuts Attack Success 10x Can Still Be the Wrong Guardrail: Reading AgentDojo Numbers Like an Engineer

#ai #security #agents #machinelearning
Comments
11 min read
Your Agent's Gate Threshold Is a Winner's Curse: Tuning Per-Action Thresholds Without Fooling Yourself
ginigenai_hp_0ae441ead91f profile

Your Agent's Gate Threshold Is a Winner's Curse: Tuning Per-Action Thresholds Without Fooling Yourself

#ai #machinelearning #security #agents
Comments
13 min read
Action Safety for Agents: Deciding What an Agent Is Allowed to Do
ginigenai_hp_0ae441ead91f profile

Action Safety for Agents: Deciding What an Agent Is Allowed to Do

#ai #machinelearning #llm #security
Comments
3 min read
오픈 퀀텀 챌린지(OQC): 재현 가능한 하드웨어 프리 양자 벤치마크
ginigenai_hp_0ae441ead91f profile

오픈 퀀텀 챌린지(OQC): 재현 가능한 하드웨어 프리 양자 벤치마크

#quantum #benchmark #opensource #ai
Comments
1 min read
Indirect Prompt Injection Through Tool Descriptions and Tool Output: How Untrusted Metadata Hijacks Agents
ginigenai_hp_0ae441ead91f profile

Indirect Prompt Injection Through Tool Descriptions and Tool Output: How Untrusted Metadata Hijacks Agents

#ai #agents #security #llm
Comments
7 min read
When Attackers Bring Their Own Agents: A Defensive Gating Playbook
ginigenai_hp_0ae441ead91f profile

When Attackers Bring Their Own Agents: A Defensive Gating Playbook

#ai #agents #security #llm
Comments
7 min read
Should Your AI Agent Act? An Engineer's Guide to Action Gates, Confidence, and the Latency Budget
ginigenai_hp_0ae441ead91f profile

Should Your AI Agent Act? An Engineer's Guide to Action Gates, Confidence, and the Latency Budget

#ai #agents #llm #security
Comments 1
13 min read
loading...