IBM's Granite LLMON Models Block 47% More Prompt Injections
IBM's Granite-4.1 LLMON previews avoided 47% more prompt-injection attacks than the best frontier model tested, cutting attack success rates to 0.02%–5.6%.
Topic
AI Security
Topic
AI Security
Fireworks AI breach exposed Notion customer chat transcripts
Fireworks AI said hackers took customer billing information and datasets. Notion said the breach affected around 1% of its custom…
Kindo Raises $30 Million to Control Enterprise AI Agents
Kindo raised $30 million, lifting total capital to $57.6 million, as the Venice Beach company expands controls for enterprise AI…
Only 29% of Security Teams Can Audit GenAI Data Flows
Only 29% of 433 security professionals can routinely count sensitive data sent to GenAI tools, while 94.2% of AI tools observed b…
No Frontier AI Lab Scores Above C+ on Security Controls
A nonprofit assessment of Anthropic, Google, Meta, OpenAI and xAI found none scored above a C+ on AI control practices. Security…
United Joins Amazon and Target in Blocking AI Shopping Agents
United Airlines banned unauthorized AI agents Wednesday, joining Amazon, Target, eBay, Booking.com, Resy and Yelp in restricting…
Low-Code and High-Code AI Agents Need Different Security Controls
Forrester found in 2024 that 87% of enterprise developers use low-code platforms. Distinct connector and execution risks require…
Hugging Face Warns Open AI Platforms Are Becoming Prime Targets
Hugging Face policy chief Irene Solaiman says open AI platforms now face attacks on API keys, model weights and billing data — an…
Grok Build Flaw Exposed 35,000 Apps, Including SpaceXSI's Own Files
Passive DNS searches surfaced 43,601 grok.me hostnames; 35,578 apps opened without login, holding SpaceXSI sales plans, Tesla sta…
Daylight Raises $80 Million to Scale AI Security Operations
Daylight raised $80 million in a Series B led by Goldman Sachs Alternatives, funding global expansion and an AI-agent security pl…
Bay Exits Stealth With $50 Million to Secure Enterprise AI Agents
Tel Aviv startup Bay exits stealth with $50M to police autonomous AI agents, claiming millisecond decisions and threefold adoptio…