Daily, Saturday 19 October 2024
Reconstructed on 19 November 2026 from archived source metadata.
From the editor
The editor's note for this issue is not available. The developments below were selected and ranked automatically from the sources listed.
Top developments
- 1
Sabotage evaluations for frontier models
A new paper on AI safety evaluations from Anthropic's Alignment Science team
- 2
Microsoft Reveals macOS Vulnerability that Bypasses Privacy Controls in Safari Browser
Microsoft has disclosed details about a now-patched security flaw in Apple's Transparency, Consent, and Control (TCC) framework in macOS that has likely come under exploitation to get around a user's privacy preferences and access data. The shortcoming, codenamed HM Surf by the…
- 3
Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing attacks primarily focus on crafting…
Further reading, by topic
Advisories in this window
- 11 npm advisories11 critical
- 2 NuGet advisories1 high · 1 moderate
- 2 Go advisories1 critical · 1 high
- 1 Maven advisory1 moderate
This edition
9 developments and 16 advisories in the window. Selection and order are automatic: how stories are placed and ranked.