Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llmsecurity
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Sanitize Context Before Every Model Review Call
Raylabs
Raylabs
Raylabs
Follow
Nov 18
Sanitize Context Before Every Model Review Call
#
llmsecurity
#
dataprivacy
#
engineeringbestpractices
Comments
Add Comment
2 min read
Moderation
Evil-GPT v2 – Exploiting an AI Chatbot Through Prompt Injection
Victor
Victor
Victor
Follow
Nov 17
Evil-GPT v2 – Exploiting an AI Chatbot Through Prompt Injection
#
tryhackme
#
llmsecurity
#
promptinjection
#
security
1
 reaction
Comments
Add Comment
6 min read
Moderation
The Concierge Knows Too Much — Prompt Injection and Social Engineering
Victor
Victor
Victor
Follow
Nov 17
The Concierge Knows Too Much — Prompt Injection and Social Engineering
#
tryhackme
#
llmsecurity
#
promptinjection
1
 reaction
Comments
Add Comment
7 min read
Moderation
NeMo Guardrails vs Guardrails AI: traces, metrics and exported data
Span Observer
Span Observer
Span Observer
Follow
Nov 10
NeMo Guardrails vs Guardrails AI: traces, metrics and exported data
#
guardrailsai
#
llmguardrails
#
llmsecurity
#
metrics
Comments
Add Comment
6 min read
Moderation
Local LLMs for Cybersecurity: Choose the Brain, Limit Its Reach
Aleksei Aleinikov
Aleksei Aleinikov
Aleksei Aleinikov
Follow
Nov 6
Local LLMs for Cybersecurity: Choose the Brain, Limit Its Reach
#
localllm
#
cybersecurity
#
llmsecurity
#
aiagentsecurity
Comments
Add Comment
15 min read
Moderation
OWASP Top 10 for LLM Applications: the three risks that become yours to enforce
AgentTrail
AgentTrail
AgentTrail
Follow
Oct 27
OWASP Top 10 for LLM Applications: the three risks that become yours to enforce
#
owasp
#
llmsecurity
#
excessiveagency
#
denialofwallet
Comments
Add Comment
8 min read
Moderation
AgentGPT: 1,022 Fingerprinted Deployments Where the Stored Secret Is an LLM API Key
andreagomez
andreagomez
andreagomez
Follow
Oct 22
AgentGPT: 1,022 Fingerprinted Deployments Where the Stored Secret Is an LLM API Key
#
zoomeye
#
agentgpt
#
llmsecurity
#
apikeyexposure
Comments
Add Comment
3 min read
Moderation
The Complete Guide to Prompt Injection Attacks: How to Protect Yourself When Using AI
Veduis
Veduis
Veduis
Follow
Oct 20
The Complete Guide to Prompt Injection Attacks: How to Protect Yourself When Using AI
#
promptinjection
#
aisecurity
#
llmsecurity
#
chatbotsafety
Comments
Add Comment
12 min read
Moderation
Counting the AI Gateway Surface: ZoomEye Data on LiteLLM and Kestra After the September KEV Batch
jeffrey
jeffrey
jeffrey
Follow
Sep 18
Counting the AI Gateway Surface: ZoomEye Data on LiteLLM and Kestra After the September KEV Batch
#
zoomeye
#
internetmeasurement
#
aiinfrastructure
#
llmsecurity
Comments
Add Comment
3 min read
Moderation
Your assistant didn't get breached. It's gossiping.
Jason Miller
Jason Miller
Jason Miller
Follow
Sep 3
Your assistant didn't get breached. It's gossiping.
#
aiprivacy
#
llmsecurity
#
contextualintegrity
#
chatbotmemory
Comments
Add Comment
3 min read
Moderation
AURA v0.1.0: Deterministic Trigger Extraction, Auditable Math & a Self-Healing Analytics Engine
Ecaterina Sevciuc
Ecaterina Sevciuc
Ecaterina Sevciuc
Follow
Sep 26
AURA v0.1.0: Deterministic Trigger Extraction, Auditable Math & a Self-Healing Analytics Engine
#
aisafety
#
llmsecurity
#
promptinjection
#
githubactions
3
 reactions
Comments
6
 comments
5 min read
Moderation
Your AI Agent’s Reasoning Isn’t as Private as You Think
Ali SĂĽleyman TOPUZ
Ali SĂĽleyman TOPUZ
Ali SĂĽleyman TOPUZ
Follow
Oct 4
Your AI Agent’s Reasoning Isn’t as Private as You Think
#
apisecurity
#
llmsecurity
#
aisecurity
Comments
Add Comment
13 min read
Moderation
Your AI Gateway Is Holding the Keys: Hardening Self-Hosted LLM Infrastructure After the LiteLLM and Starlette KEV Additions
yutianle
yutianle
yutianle
Follow
Sep 17
Your AI Gateway Is Holding the Keys: Hardening Self-Hosted LLM Infrastructure After the LiteLLM and Starlette KEV Additions
#
cybersecurity
#
aiinfrastructure
#
authentication
#
llmsecurity
Comments
1
 comment
3 min read
Moderation
I Spent My Weekend Reading the Paper That Cracked Every Major LLM’s “Encrypted” Reasoning, and It’s…
Ali SĂĽleyman TOPUZ
Ali SĂĽleyman TOPUZ
Ali SĂĽleyman TOPUZ
Follow
Sep 13
I Spent My Weekend Reading the Paper That Cracked Every Major LLM’s “Encrypted” Reasoning, and It’s…
#
anthropicclaude
#
aisecurity
#
llmsecurity
Comments
1
 comment
13 min read
Moderation
What a Bad Week of AI Agent Headlines Actually Teaches About Oversight
Ali SĂĽleyman TOPUZ
Ali SĂĽleyman TOPUZ
Ali SĂĽleyman TOPUZ
Follow
Sep 6
What a Bad Week of AI Agent Headlines Actually Teaches About Oversight
#
agenticai
#
cybersecurity
#
llmsecurity
#
aisafety
Comments
Add Comment
14 min read
Moderation
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account