
CEO, Founder https://teapawt.org/t.co/kcudRon3m0 AI Red Teaming Visionary, Cybersecurity Veteran #SecureAI #LLMSecurity #AISafety
tel aviv
Joined April 2010
- Tweets2.4K
- Following1.8K
- Followers3.4K
- Likes789
Alex Polyakov retweeted
wowwwww. this is a VERY similar example to my tip below, but using something like "respond quickly" to get to a smaller less-secure model so you can bypass safety mechanisms:
adversa.ai/blog/promisqroute…
Alex Polyakov retweeted
GPT-5 AI Router Novel Vulnerability Class Exposes the Fatal Flaw in Multi-Model Architectures - adversa.ai/blog/promisqroute… by @Adversa_AI
Security researchers from Adversa AI discovered that ChatGPT 5 have a fatal flaw: they can route your requests to cheaper, less secure models to save money. Attackers can exploit this to bypass AI security and safety measures with just a few words.
What Is PROMISQROUTE?
When you use ChatGPT or any major AI service, you think you’re talking to one AI model. You’re not. Behind the scenes, a “router” reads your message and decides which of many models should answer—usually picking the cheapest one, not the safest.
Meet PROMISQROUTE — a fundamentally new AI vulnerability that abuses AI routing mechanism to trigger SSRF-style bypass in multimodal infrastructure leading to ChatGPT Model Downgrade and Jailbreak exploitation as an example.
The real answer to WHY its was so easy to Jailbreak GPT-5
PROMISQROUTE = Prompt-based Router Open-Mode Manipulation Induced via SSRF-like Queries, Reconfiguring Operations Using Trust Evasion. (Yes, we took this vulnerability naming craziness to meta-layer
#AISecurity #LLMSecurity #AgenticAI #ModelRouting #PromptInjection #SSRFAnalogy #SafetyByDesign #SecureAI #RedTeamAI #TrustBoundaries #PostFilter #ModelAttestation #LeastPrivilege #OpenAI #GPT5 #Autoswitching #RiskManagement #AICompliance #ThreatModeling #DefenseInDepth #AIGovernance #SecureByDefault
Alex Polyakov retweeted
The following in priority order can help in a security review setting: 1) take an x-ray to the product and show owners exactly what risks they're exposing themselves to inform their risk tolerance choices, 2) apply access control and least privilege to restrict LLM privileges ...
Alex Polyakov retweeted
Biometric security checks – from voice recognition, to face and fingerprint scans – are under threat from artificial intelligence, but what can we do about it?
https://teapawt.org/t.co/1r34r7j64X
Alex Polyakov retweeted
Experts Use Jailbreaks and Prompt Injection Attacks to Bypass Safety Measures, China tightens security regulations, a new book on Secure AI and other news read in our weekly digest.
Credits: Jim Dempsey
#SecureAI #TrustedAI #AdversarialAI
adversa.ai/blog/towards-trus…
Alex Polyakov retweeted
The Security Risks of AI Language Models: A Looming Disaster, The AI Revolution, Addressing the Unique Threats and Legal Ambiguities of AI Security Breaches in our weekly digest.
Credits: @Melissahei, @kevtownsend
#SecureAI #TrustedAI #AdversarialAI
adversa.ai/blog/towards-trus…
Alex Polyakov retweeted
It's all downhill from here...
Security researchers, technologists, and computer scientists are developing jailbreaks and prompting injection attacks against ChatGPT and other generative AI systems. wired.trib.al/DmNGztn
Alex Polyakov retweeted
GPT-4 jailbreaks and hacks dropped by @adversa_ai AI safety research team few hours after the release, buy buy DAN, welcome RabbitHole.
#gpt4 #dan #aisafety #secureAI #trustedAI #responsibleai
adversa.ai/blog/gpt-4-hackin…
Alex Polyakov retweeted
After coining the term MLSecOps in 2017, I'm finally presenting the best you ever saw introduction to MLSecOps, or DevSecOps for AI systems, with core principles, ML pipeline stages, and examples!
Slides and Video: conf42.com/DevSecOps_2022_Eu…
#AI #SecureAI #MLSecOps #DevSecOps
Alex Polyakov retweeted
40% of Organizations already experienced privacy breaches or security incidents with AI according to the latest Gartner survey.
Credits: Robert Lemos, Harriet Farlow, Avivah Litan
#SecureAI #TrustedAI #AdversarialAI
adversa.ai/blog/towards-trus…
Alex Polyakov retweeted
Alex Polyakov @DontTrustAI delivered a presentation dedicated to importance of Threat Modeling and security assessment for AI at the @mlconference
#MLConference #ML #MLCon #SecureAI #TrustedAI #AdversarialAI
adversa.ai/blog/threat-model…
Alex Polyakov retweeted
Replying to @DontTrustAI
@DontTrustAI will show you how to deal with ML algorithm’s #security #assessment, how to define a #threat model, what #metrics to choose, what approaches to protection can be applied and where. Join the session now and don't miss out!
@mlconference #ML #MLCon
Alex Polyakov retweeted
📢@haydenfield from @MorningBrew covered the rise of AI red teams and highlights the work done by the @Microsoft AI Red Team
Some liner notes on red teaming real-world ML systems 🧵
emergingtechbrew.com/stories…
Alex Polyakov retweeted
Nice tip from @joshua_saxe on evaluating vendors' ML solutions:
1. Go to scholar.google.com
2. Type in vendor's name and see their publications
Alex Polyakov retweeted
Honorlock concluded that a college student was cheating during an exam in February - do you think this is fair or not? Read more in our weekly digest.
Credits: @bendee983, @kashhill
#SecureAI #TrustedAI #AdversarialAI
adversa.ai/towards-trusted-a…
Alex Polyakov retweeted
One of my favorite possessions is my twitter picture which, if run through PimEyes, mostly returns pictures of Mark Zuckerberg, thanks to @DontTrustAI
For a story on a paid facial recognition service called PimEyes, my colleagues graciously volunteered their faces to show just how alarmingly effective it can be in finding photos of someone on the internet. nytimes.com/2022/05/26/techn…
Alex Polyakov retweeted
Specialists should be prepared for the upcoming AI poisoning apocalypse - see more details in our new weekly news digest!
Credits: @tculpan
#SecureAI #TrustedAI #ResponsibleAI
adversa.ai/blog/towards-trus…
Alex Polyakov retweeted
Supply chain attacks on AI are double trouble - hurry up and have a took at a new article by Adversa founder @DontTrustAI ✨
#SecureAI #TrustedAI #AdversarialAI
forbes.com/sites/forbestechc…
Alex Polyakov retweeted
The Art Exhibition That Fools Facial Recognition Systems - securityweek.com/art-exhibit…
Alex Polyakov retweeted
April Fool's Day is when we decided to...🤪
Launch the world-first Art Gallery of exploits 🔥
Which can fool AI face recognition in the form of NFT🤣
#NFT #Cyber #FaceRecognition #SecureAI #TrustedAI #AdversarialAI
adversa.ai/fool-ai-nft-art-e…

























