MastodonTech.de

TechnoTenshi :verified_trans: :Fire_Lesbian:Supabase's MCP is vulnerable to "lethal trifecta" attacks where LLMs with elevated DB access, exposed to user input, can be tricked into leaking sensitive data. Read-only mode helps but doesn't eliminate risk. <a href="https://simonwillison.net/2025/Jul/6/supabase-mcp-lethal-trifecta/" rel="nofollow noopener" translate="no" target="_blank">https://simonwillison.net/2025/Jul/6/supabase-mcp-lethal-trifecta/</a><a href="https://infosec.exchange/tags/PromptInjection" class="mention hashtag" rel="nofollow noopener" target="_blank">#PromptInjection</a> <a href="https://infosec.exchange/tags/LLMSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMSecurity</a> <a href="https://infosec.exchange/tags/Supabase" class="mention hashtag" rel="nofollow noopener" target="_blank">#Supabase</a> <a href="https://infosec.exchange/tags/Infosec" class="mention hashtag" rel="nofollow noopener" target="_blank">#Infosec</a>

OWASP Foundation🚨 Time is running out to register for OWASP Global AppSec EU 2025 in Barcelona from May 27–31!This event is for builders, breakers, defenders, leaders, and all others who want to engage with the best minds in AppSec, explore emerging tech like AI and LLM security, and connect with OWASP project leaders.🔗 Register now: <a href="https://owasp.glueup.com/event/123983/register" rel="nofollow noopener" translate="no" target="_blank">https://owasp.glueup.com/event/123983/register</a><a href="https://infosec.exchange/tags/OWASP" class="mention hashtag" rel="nofollow noopener" target="_blank">#OWASP</a> <a href="https://infosec.exchange/tags/AppSecEU2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#AppSecEU2025</a> <a href="https://infosec.exchange/tags/Cybersecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#Cybersecurity</a> <a href="https://infosec.exchange/tags/AppSec" class="mention hashtag" rel="nofollow noopener" target="_blank">#AppSec</a> <a href="https://infosec.exchange/tags/DevSecOps" class="mention hashtag" rel="nofollow noopener" target="_blank">#DevSecOps</a> <a href="https://infosec.exchange/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://infosec.exchange/tags/LLMSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMSecurity</a> <a href="https://infosec.exchange/tags/Hacking" class="mention hashtag" rel="nofollow noopener" target="_blank">#Hacking</a> <a href="https://infosec.exchange/tags/InfoSec" class="mention hashtag" rel="nofollow noopener" target="_blank">#InfoSec</a> <a href="https://infosec.exchange/tags/Barcelona" class="mention hashtag" rel="nofollow noopener" target="_blank">#Barcelona</a>

OWASP FoundationJoin Juan Berner at OWASP Global AppSec EU 2025 in Barcelona for an exciting session exploring the future of Web Application Firewalls with AI! 🛡️ From Prompt to Protect: LLMs as Next-Gen WAFs 📅 Thursday, May 29, 2025 ⏰ 1:15 PM – 2:00 PM CEST 🔗 Register: <a href="https://owasp.glueup.com/event/123983/register/" rel="nofollow noopener" translate="no" target="_blank">https://owasp.glueup.com/event/123983/register/</a> <a href="https://infosec.exchange/tags/OWASP" class="mention hashtag" rel="nofollow noopener" target="_blank">#OWASP</a> <a href="https://infosec.exchange/tags/AppSecEU2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#AppSecEU2025</a> <a href="https://infosec.exchange/tags/LLMsecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMsecurity</a> <a href="https://infosec.exchange/tags/WAF" class="mention hashtag" rel="nofollow noopener" target="_blank">#WAF</a> <a href="https://infosec.exchange/tags/AIinCybersecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIinCybersecurity</a> <a href="https://infosec.exchange/tags/NextGenSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#NextGenSecurity</a> <a href="https://infosec.exchange/tags/SecureApps" class="mention hashtag" rel="nofollow noopener" target="_blank">#SecureApps</a> <a href="https://infosec.exchange/tags/Barcelona" class="mention hashtag" rel="nofollow noopener" target="_blank">#Barcelona</a>

Frank J🔐 Gamma AI is now being used to craft pixel-perfect phishing pages. These attacks mimic cloud login portals, flip JavaScript behavior, and bypass email filters.📉 We break it all down in our latest article: — Real misuse cases — MITRE TTP matrix — Python detection script — Visual trust infographic📖 Read it here: <a href="https://open.substack.com/pub/teamivity/p/weaponized-intelligence-how-gamma?r=3cbcvp&utm_medium=ios" rel="nofollow noopener" translate="no" target="_blank">https://open.substack.com/pub/teamivity/p/weaponized-intelligence-how-gamma?r=3cbcvp&utm_medium=ios</a><a href="https://ioc.exchange/tags/CyberSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#CyberSecurity</a> <a href="https://ioc.exchange/tags/GammaAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#GammaAI</a> <a href="https://ioc.exchange/tags/LLMSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMSecurity</a> <a href="https://ioc.exchange/tags/CloudSec" class="mention hashtag" rel="nofollow noopener" target="_blank">#CloudSec</a> <a href="https://ioc.exchange/tags/Phishing" class="mention hashtag" rel="nofollow noopener" target="_blank">#Phishing</a> <a href="https://ioc.exchange/tags/Infosec" class="mention hashtag" rel="nofollow noopener" target="_blank">#Infosec</a>

OWASP FoundationJoin Javan Rasokat and Rico Komenda at OWASP Global AppSec EU 2025 in Barcelona for a powerful joint session on AI security! 🛠️Builders and Breakers: A Collaborative Look at Securing LLM-Integrated Apps 📅 Thursday, May 29, 2025 ⏰ 2:15 PM – 3:00 PM CEST 🔗 Register: <a href="https://owasp.glueup.com/event/123983/register/" rel="nofollow noopener" translate="no" target="_blank">https://owasp.glueup.com/event/123983/register/</a> <a href="https://infosec.exchange/tags/OWASP" class="mention hashtag" rel="nofollow noopener" target="_blank">#OWASP</a> <a href="https://infosec.exchange/tags/AppSecEU2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#AppSecEU2025</a> <a href="https://infosec.exchange/tags/AIsecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIsecurity</a> <a href="https://infosec.exchange/tags/LLMSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMSecurity</a> <a href="https://infosec.exchange/tags/Cybersecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#Cybersecurity</a> <a href="https://infosec.exchange/tags/RedTeam" class="mention hashtag" rel="nofollow noopener" target="_blank">#RedTeam</a> <a href="https://infosec.exchange/tags/BlueTeam" class="mention hashtag" rel="nofollow noopener" target="_blank">#BlueTeam</a> <a href="https://infosec.exchange/tags/SecureAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#SecureAI</a> <a href="https://infosec.exchange/tags/Barcelona" class="mention hashtag" rel="nofollow noopener" target="_blank">#Barcelona</a>

JCONHow secure is your LLM-powered app, really?Join 🧑🏼‍💻 Brian Vermeer and Lize Raes at <a href="https://mastodon.social/tags/JCON2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#JCON2025</a> as they tackle the dark side of AI: ⚠️ Prompt injection 🔐 Key leakage 📉 Data abuse risks 💡 And how YOUR system vulnerabilities impact <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> behavior. Get practical strategies to build secure & privacy-compliant <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLM</a> applications—because your AI shouldn’t turn against you. 😉🎟️ <a href="https://2025.europe.jcon.one/tickets" rel="nofollow noopener" translate="no" target="_blank">https://2025.europe.jcon.one/tickets</a> <a href="https://mastodon.social/tags/Java" class="mention hashtag" rel="nofollow noopener" target="_blank">#Java</a> <a href="https://mastodon.social/tags/LLMSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMSecurity</a> <a href="https://mastodon.social/tags/JavaChampion" class="mention hashtag" rel="nofollow noopener" target="_blank">#JavaChampion</a> <a href="https://mastodon.social/tags/DevSecOps" class="mention hashtag" rel="nofollow noopener" target="_blank">#DevSecOps</a> <a href="https://mastodon.social/tags/JCON" class="mention hashtag" rel="nofollow noopener" target="_blank">#JCON</a> <a href="https://mastodon.social/tags/JavaCommunity" class="mention hashtag" rel="nofollow noopener" target="_blank">#JavaCommunity</a>

Pyrzout :vm:DeepSeek Claims ‘Malicious Attacks’ After AI Breakthrough Upends NVIDIA, Broadcom <a href="https://thecyberexpress.com/deepseek-malicious-attacks-ai-breakthrough/" rel="nofollow noopener" translate="no" target="_blank">https://thecyberexpress.com/deepseek-malicious-attacks-ai-breakthrough/</a> <a href="https://social.skynetcloud.site/tags/largelanguagemodels" class="mention hashtag" rel="nofollow noopener" target="_blank">#largelanguagemodels</a> <a href="https://social.skynetcloud.site/tags/TheCyberExpressNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#TheCyberExpressNews</a> <a href="https://social.skynetcloud.site/tags/TheCyberExpress" class="mention hashtag" rel="nofollow noopener" target="_blank">#TheCyberExpress</a> <a href="https://social.skynetcloud.site/tags/FirewallDaily" class="mention hashtag" rel="nofollow noopener" target="_blank">#FirewallDaily</a> <a href="https://social.skynetcloud.site/tags/Cyberattack" class="mention hashtag" rel="nofollow noopener" target="_blank">#Cyberattack</a> <a href="https://social.skynetcloud.site/tags/LLMsecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMsecurity</a> <a href="https://social.skynetcloud.site/tags/CyberNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#CyberNews</a> <a href="https://social.skynetcloud.site/tags/DeepSeek" class="mention hashtag" rel="nofollow noopener" target="_blank">#DeepSeek</a> <a href="https://social.skynetcloud.site/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#ChatGPT</a> <a href="https://social.skynetcloud.site/tags/OpenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#OpenAI</a> <a href="https://social.skynetcloud.site/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a>

Andrei KucharavyGiving a talk today at the Swiss <a href="https://mastodon.social/tags/CISOSummit" class="mention hashtag" rel="nofollow noopener" target="_blank">#CISOSummit</a> in the margin of the <a href="https://mastodon.social/tags/SwissCyberStorm" class="mention hashtag" rel="nofollow noopener" target="_blank">#SwissCyberStorm</a> about the LLMs in cybersecurity, current hype, and the lessons from the last few decades to provide them with tools to make informed decisions. <a href="https://mastodon.social/tags/LLMSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMSecurity</a> <a href="https://mastodon.social/tags/cybersecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#cybersecurity</a> <a href="https://mastodon.social/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMs</a><a href="https://www.ciso-summit.ch/next-summit/" rel="nofollow noopener" translate="no" target="_blank">https://www.ciso-summit.ch/next-summit/</a>

DeepSec Conference ☑DeepSec 2024 Training: AI SecureOps: Attacking & Defending GenAI Applications and Services – Abhinav SinghAcquire hands-on experience in GenAI and LLM security through CTF-styled training, tailored to real-world attacks and defense scenarios. Dive into protecting bot<a href="https://blog.deepsec.net/deepsec-2024-training-ai-secureops-attacking-defending-genai-applications-and-services-abhinav-singh/" rel="nofollow noopener" translate="no" target="_blank">https://blog.deepsec.net/deepsec-2024-training-ai-secureops-attacking-defending-genai-applications-and-services-abhinav-singh/</a><a href="https://social.tchncs.de/tags/Conference" class="mention hashtag" rel="nofollow noopener" target="_blank">#Conference</a> <a href="https://social.tchncs.de/tags/Training" class="mention hashtag" rel="nofollow noopener" target="_blank">#Training</a> <a href="https://social.tchncs.de/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#ArtificialIntelligence</a> <a href="https://social.tchncs.de/tags/DeepSec2024" class="mention hashtag" rel="nofollow noopener" target="_blank">#DeepSec2024</a> <a href="https://social.tchncs.de/tags/GenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#GenAI</a> <a href="https://social.tchncs.de/tags/LLMSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMSecurity</a> <a href="https://social.tchncs.de/tags/Training" class="mention hashtag" rel="nofollow noopener" target="_blank">#Training</a>

IT NewsAI poisoning could turn open models into destructive “sleeper agents,” says Anthropic - Enlarge (credit: Benj Edwards | Getty Images) Imagine download... - <a href="https://arstechnica.com/?p=1995975" rel="nofollow noopener" translate="no" target="_blank">https://arstechnica.com/?p=1995975</a> <a href="https://schleuss.online/tags/largelanguagemodels" class="mention hashtag" rel="nofollow noopener" target="_blank">#largelanguagemodels</a> <a href="https://schleuss.online/tags/promptinjections" class="mention hashtag" rel="nofollow noopener" target="_blank">#promptinjections</a> <a href="https://schleuss.online/tags/sleeperagents" class="mention hashtag" rel="nofollow noopener" target="_blank">#sleeperagents</a> <a href="https://schleuss.online/tags/llmsecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#llmsecurity</a> <a href="https://schleuss.online/tags/aisecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#aisecurity</a> <a href="https://schleuss.online/tags/anthropic" class="mention hashtag" rel="nofollow noopener" target="_blank">#anthropic</a> <a href="https://schleuss.online/tags/chatgpt" class="mention hashtag" rel="nofollow noopener" target="_blank">#chatgpt</a> <a href="https://schleuss.online/tags/chatgtp" class="mention hashtag" rel="nofollow noopener" target="_blank">#chatgtp</a> <a href="https://schleuss.online/tags/claude2" class="mention hashtag" rel="nofollow noopener" target="_blank">#claude2</a> <a href="https://schleuss.online/tags/biz" class="mention hashtag" rel="nofollow noopener" target="_blank">#biz</a>⁢ <a href="https://schleuss.online/tags/claude" class="mention hashtag" rel="nofollow noopener" target="_blank">#claude</a> <a href="https://schleuss.online/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#llm</a> <a href="https://schleuss.online/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a>

William GunnOk, it's time to admit that RLHF is not an effective safeguard for open release of LLMs. I know there are a lot of people ideologically committed to open source, but this is messed up: <a href="https://www.lesswrong.com/posts/3eqHYxfWb5x4Qfz8C/unrlhf-efficiently-undoing-llm-safeguards" rel="nofollow noopener" translate="no" target="_blank">https://www.lesswrong.com/posts/3eqHYxfWb5x4Qfz8C/unrlhf-efficiently-undoing-llm-safeguards</a> <a href="https://www.lesswrong.com/posts/qmQFHCgCyEEjuy5a7/lora-fine-tuning-efficiently-undoes-safety-training-from" rel="nofollow noopener" translate="no" target="_blank">https://www.lesswrong.com/posts/qmQFHCgCyEEjuy5a7/lora-fine-tuning-efficiently-undoes-safety-training-from</a> <a href="https://mastodon.social/tags/llms" class="mention hashtag" rel="nofollow noopener" target="_blank">#llms</a> <a href="https://mastodon.social/tags/llmsecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#llmsecurity</a> <a href="https://mastodon.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://mastodon.social/tags/aisafety" class="mention hashtag" rel="nofollow noopener" target="_blank">#aisafety</a> <a href="https://mastodon.social/tags/artificialintelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#artificialintelligence</a> <a href="https://mastodon.social/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#opensource</a>

Frühere Suchanfragen

Suchoptionen

Verwaltet von:

Serverstatistik:

#llmsecurity