Tag: protective measures
-
New York Times – Artificial Intelligence : Has Britain Gone Too Far With Its Digital Controls?
Source URL: https://www.nytimes.com/2025/09/17/technology/britain-facial-recognition-digital-controls.html Source: New York Times – Artificial Intelligence Title: Has Britain Gone Too Far With Its Digital Controls? Feedly Summary: British authorities have ramped up the use of facial recognition, artificial intelligence and internet regulation to address crime and other issues, stoking concerns of surveillance overreach. AI Summary and Description: Yes Summary: The…
-
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…
-
Wired: Psychological Tricks Can Get AI to Break the Rules
Source URL: https://arstechnica.com/science/2025/09/these-psychological-tricks-can-get-llms-to-respond-to-forbidden-prompts/ Source: Wired Title: Psychological Tricks Can Get AI to Break the Rules Feedly Summary: Researchers convinced large language model chatbots to comply with “forbidden” requests using a variety of conversational tactics. AI Summary and Description: Yes Summary: The text discusses researchers’ exploration of conversational tactics used to manipulate large language model (LLM)…
-
The Register: Crims claim HexStrike AI penetration tool makes quick work of Citrix bugs
Source URL: https://www.theregister.com/2025/09/03/hexstrike_ai_citrix_exploits/ Source: The Register Title: Crims claim HexStrike AI penetration tool makes quick work of Citrix bugs Feedly Summary: LLMs and 0-days – what could possibly go wrong? Attackers on underground forums claimed they were using HexStrike AI, an open-source red-teaming tool, against Citrix NetScaler vulnerabilities within hours of disclosure, according to Check…
-
The Register: Internet mapping and research tool Censys reveals state-based abuse, harassment
Source URL: https://www.theregister.com/2025/09/03/censys_abuse_sigcomm_paper/ Source: The Register Title: Internet mapping and research tool Censys reveals state-based abuse, harassment Feedly Summary: ‘Universities are being used to proxy offensive government operations, turning research access decisions political’ Censys Inc, vendor of the popular Censys internet-mapping tool, has revealed that state-based actors are trying to abuse its services by hiding…
-
Slashdot: One Long Sentence is All It Takes To Make LLMs Misbehave
Source URL: https://slashdot.org/story/25/08/27/1756253/one-long-sentence-is-all-it-takes-to-make-llms-misbehave?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: One Long Sentence is All It Takes To Make LLMs Misbehave Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a significant security research finding from Palo Alto Networks’ Unit 42 regarding vulnerabilities in large language models (LLMs). The researchers explored methods that allow users to bypass…
-
Schneier on Security: We Are Still Unable to Secure LLMs from Malicious Inputs
Source URL: https://www.schneier.com/blog/archives/2025/08/we-are-still-unable-to-secure-llms-from-malicious-inputs.html Source: Schneier on Security Title: We Are Still Unable to Secure LLMs from Malicious Inputs Feedly Summary: Nice indirect prompt injection attack: Bargury’s attack starts with a poisoned document, which is shared to a potential victim’s Google Drive. (Bargury says a victim could have also uploaded a compromised file to their own…
-
The Register: Citrix patches trio of NetScaler bugs – after attackers beat them to it
Source URL: https://www.theregister.com/2025/08/26/citrix_patches_trio_of_netscaler/ Source: The Register Title: Citrix patches trio of NetScaler bugs – after attackers beat them to it Feedly Summary: Criminals already abusing its latest zero-days Citrix has pushed out fixes for three fresh NetScaler holes – and yes, they’ve already been used in the wild before the vendor got around to patching.……
-
The Register: One long sentence is all it takes to make LLMs misbehave
Source URL: https://www.theregister.com/2025/08/26/breaking_llms_for_fun/ Source: The Register Title: One long sentence is all it takes to make LLMs misbehave Feedly Summary: Chatbots ignore their guardrails when your grammar sucks, researchers find Security researchers from Palo Alto Networks’ Unit 42 have discovered the key to getting large language model (LLM) chatbots to ignore their guardrails, and it’s…