Avatar

Capt. AIn

Captain@infosec.pub
Joined
26 posts • 0 comments
Direct message
Filter:
OverviewPostsComments
Sort:
NewOldTopAll
1

Identifying AI-generated images with SynthID(www.deepmind.com)

posted
by
Avatar
Capt. AIn@infosec.pubM
in
Avatar
ai_infosec@infosec.pub
0 comments
hidereport
1

Thinking about the security of AI systems(www.ncsc.gov.uk)

posted
by
Avatar
Capt. AIn@infosec.pubM
in
Avatar
ai_infosec@infosec.pub
0 comments
hidereport
1

GitHub - google/model-transparency(github.com)

posted
by
Avatar
Capt. AIn@infosec.pubM
in
Avatar
ai_infosec@infosec.pub
0 comments
hidereport
1

Universal and Transferable Attacks on Aligned Language Models(llm-attacks.org)

posted
by
Avatar
Capt. AIn@infosec.pubM
in
Avatar
ai_infosec@infosec.pub
0 comments
hidereport
1

Cybercriminals train AI chatbots for phishing, malware attacks(www.bleepingcomputer.com)

posted
by
Avatar
Capt. AIn@infosec.pubM
in
Avatar
ai_infosec@infosec.pub
0 comments
hidereport
1

Adversarial suffixes that circumvent the alignment of open source LLMS, ChatGPT, Claude, Bard, and LLaMA-2(twitter.com)

posted
by
Avatar
Capt. AIn@infosec.pubM
in
Avatar
ai_infosec@infosec.pub
0 comments
hidereport
1

(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs(twitter.com)

posted
by
Avatar
Capt. AIn@infosec.pubM
in
Avatar
ai_infosec@infosec.pub
0 comments
hidereport
1

Intro to ML Safety - Free course(course.mlsafety.org)

posted
by
Avatar
Capt. AIn@infosec.pubM
in
Avatar
ai_infosec@infosec.pub
0 comments
hidereport
1

Army looking at the possibility of 'AI BOMs'(defensescoop.com)

posted
by
Avatar
Capt. AIn@infosec.pubM
in
Avatar
ai_infosec@infosec.pub
0 comments
hidereport
1

Socket AI – using ChatGPT to examine every npm and PyPI package for security issues(socket.dev)

posted
by
Avatar
Capt. AIn@infosec.pubM
in
Avatar
ai_infosec@infosec.pub
0 comments
hidereport
Next page