Install
Model Security
Prompt injection, jailbreaks and poisoned data.
- 37 Tracked terms
- Last 30 days Feed window
What this topic collects on
An article joins this feed when it matches these terms. Each one is also a search of its own.
- artificial intelligence
- ai
- artificial-intelligence
- artificial intelligence (ai)
- ai (artificial intelligence)
- ai artificial intelligence
- artificialintelligence
- a.i.
- generative ai
- genai
- gen ai
- machine learning
- deep learning
- llm
- llms
- large language model
- large language models
- agentic ai
- neural networks
- prompt injection
- jailbreak
- vulnerability
- exploit
- data poisoning
- security
- guardrails
- researchers
- openai
- anthropic
- jailbreaks
- vulnerabilities
- exploits
- securities
- researcher
- anthropics
- mythos
- computer security
Related topics
Latest in Model Security
Former Anthropic researcher calls for mandatory AI kill switches as extinction risk debate heats up
1+ hour, 21+ min ago (209+ words) A resignation, a bipartisan bill, and an 86% public mandate signal that the AI safety conversation has moved well past theory Logo via Wikimedia Commons; license to verify on approval Jacob Coxon resigned from Anthropic on September 9, 2026. Four days later, he…...
Russell Fry and Suhas Subramanyam launch bipartisan Innovators Caucus to back small AI businesses
43+ min ago (261+ words) The new congressional caucus pairs a Republican from South Carolina with a Democrat from Virginia to tackle funding gaps and regulatory headaches facing smaller AI companies. Two House members from opposite sides of the aisle are betting that America’s AI…...
OpenAI acquires Glass Imaging in deal valued over $300M
1+ min ago (162+ words) The deal brings AI-enhanced camera technology into OpenAI's growing portfolio of acquisitions Logo via Wikimedia Commons; treatment-A cover, license to verify on approval OpenAI has acquired Glass Imaging, a startup developing AI powered smartphone camera technology, in a deal valuing…...
Palo Alto Networks and rivals surge as AI leaders warn of new cyber threats
18+ hour, 24+ min ago (307+ words) Palo Alto, CrowdStrike and Zscaler are all up around 15% as investors bet that growing concerns over increasingly capable AI systems could drive greater demand for cybersecurity solutions. Cybersecurity stocks are surging on Wall Street as growing concerns about the risks…...
Nvidia Palantir curb use of Anthropic models over data fears
11+ hour, 44+ min ago (230+ words) Want your own hosted, self-optimizing clone of this — or any OpenServe site? Open Development for enterprise → © OpenServe Holdings LLC Where do you stand? What each side asserts, disputes — or leaves out entirely. Whose framing of this story rings truest to…...
OpenAI's malicious bot swarm attacked RubyGems
24+ min ago (865+ words) OpenAI agents appear to have flooded RubyGems with malicious packages, adding to a near-daily deluge of rogue AI models engaging in potentially unlawful activity while their human creators face growing questions over responsibility for their agents’ bad behavior. A swarm…...
Data Governance for the Agentic Era
1+ hour, 55+ min ago (1390+ words) This article explores how modern data governance and AI-ready architecture help enterprises manage data quality, risk, compliance, and AI at scale. The modern enterprise generates and consumes unprecedented volumes of data across operational systems, customer interactions, partner ecosystems, cloud applications,…...
Fake CAPTCHAs are tricking people into hacking their own computers, and it's working
1+ hour, 5+ min ago (27+ words) Typical ClickFix social engineering attacks begin with a pop-up displayed over a trusted web page that provides some pressing instructions. Cybercriminals have weaponized CAPTCHA overlay windows to......
Anthropic targets financial advisers with new Claude tool
1+ hour, 42+ min ago (188+ words) Sept 14 (Reuters) – AI lab Anthropic on Monday launched a set of tools for financial advisers, connecting its Claude chatbot to investment analytics and wealth-management software from firms including BlackRock, Charles Schwab and Addepar. The product, called Claude for Financial Advisors,…...
Microsoft’s new AI rulebook puts human control above everything else
1+ hour, 12+ min ago (544+ words) Microsoft today published a draft “Humanist AI Code of Conduct,” a rulebook meant to guide how its MAI models behave, and it opens with a blunt promise: People matter more than AI. The document lands just days after Anthropic CEO…...