Tag: adversarial attacks
-
Unit 42: The Risks of Code Assistant LLMs: Harmful Content, Misuse and Deception
Source URL: https://unit42.paloaltonetworks.com/code-assistant-llms/ Source: Unit 42 Title: The Risks of Code Assistant LLMs: Harmful Content, Misuse and Deception Feedly Summary: We examine security weaknesses in LLM code assistants. Issues like indirect prompt injection and model misuse are prevalent across platforms. The post The Risks of Code Assistant LLMs: Harmful Content, Misuse and Deception appeared first…
-
The Register: Bot shots: US Army enlists AI startup to provide target-tracking
Source URL: https://www.theregister.com/2025/09/05/us_army_enlists_ai_startup/ Source: The Register Title: Bot shots: US Army enlists AI startup to provide target-tracking Feedly Summary: Because handing battlefield ID to an algorithm has never gone wrong before, right? The US Army is preparing to deploy a new AI product that promises to automatically identify and track potential targets on the battlefield.…
-
The Register: LegalPwn: Tricking LLMs by burying badness in lawyerly fine print
Source URL: https://www.theregister.com/2025/09/01/legalpwn_ai_jailbreak/ Source: The Register Title: LegalPwn: Tricking LLMs by burying badness in lawyerly fine print Feedly Summary: Trust and believe – AI models trained to see ‘legal’ doc as super legit Researchers at security firm Pangea have discovered yet another way to trivially trick large language models (LLMs) into ignoring their guardrails. Stick…
-
The Register: Little LLM on the RAM: Google’s Gemma 270M hits the scene
Source URL: https://www.theregister.com/2025/08/15/little_llm_on_the_ram/ Source: The Register Title: Little LLM on the RAM: Google’s Gemma 270M hits the scene Feedly Summary: A tiny model trained on trillions of tokens, ready for specialized tasks Google has unveiled a pint-sized new addition to its “open" large language model lineup: Gemma 3 270M.… AI Summary and Description: Yes Summary:…
-
OpenAI : GPT-5 and the new era of work
Source URL: https://openai.com/index/gpt-5-new-era-of-work Source: OpenAI Title: GPT-5 and the new era of work Feedly Summary: GPT-5 is OpenAI’s most advanced model—transforming enterprise AI, automation, and workforce productivity in the new era of intelligent work. AI Summary and Description: Yes Summary: The text highlights the launch of GPT-5 by OpenAI, emphasizing its potential impacts on enterprise…
-
Wired: OpenAI Announces Massive US Government Partnership
Source URL: https://www.wired.com/story/openai-is-giving-chatgpt-federal-workers/ Source: Wired Title: OpenAI Announces Massive US Government Partnership Feedly Summary: The ChatGPT maker is providing its frontier AI models to federal agencies for $1 for the next year. AI Summary and Description: Yes Summary: The offering of frontier AI models to federal agencies for a nominal fee highlights significant implications for…
-
Cisco Security Blog: Cisco’s Foundation AI Advances AI Supply Chain Security With Hugging Face
Source URL: https://feedpress.me/link/23535/17111768/ciscos-foundation-ai-advances-ai-supply-chain-security-with-hugging-face Source: Cisco Security Blog Title: Cisco’s Foundation AI Advances AI Supply Chain Security With Hugging Face Feedly Summary: Cisco’s Foundation AI is partnering with Hugging Face, bringing together the world’s leading AI model hub with Cisco’s security expertise. AI Summary and Description: Yes Summary: Cisco’s Foundation AI collaboration with Hugging Face exemplifies…
-
Cisco Security Blog: Securing an Exponentially Growing (AI) Supply Chain
Source URL: https://feedpress.me/link/23535/17085587/securing-an-exponentially-growing-ai-supply-chain Source: Cisco Security Blog Title: Securing an Exponentially Growing (AI) Supply Chain Feedly Summary: Foundation AI’s Cerberus is a 24/7 guard for the AI supply chain, analyzing models as they enter HuggingFace and sharing results to Cisco Security products. AI Summary and Description: Yes Summary: Foundation AI’s Cerberus introduces a continuous monitoring…