Daily, Tuesday 18 June 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
High-severity vulnerabilities affect a wide range of Asus router models
Many models receive patches; others will need to be replaced.
- 2
Refusal in Language Models Is Mediated by a Single Direction
Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its underlying mechanisms remain poorly…
- 3
Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
Large language models (LLMs) have been increasingly applied to various domains, which triggers increasing concerns about LLMs' safety on specialized domains, e.g. medicine. Despite prior explorations on general jailbreaking attacks, there are two challenges for applying…
Further reading, by topic
Models
- 4
- 5
Advisories in this window
- 16 npm advisories8 critical · 3 high · 5 moderate
- 4 Go advisories1 critical · 3 high
- 2 PyPI advisories1 high · 1 moderate
- 2 Maven advisories1 critical · 1 high
- 1 Packagist advisory1 moderate
This edition
10 developments and 25 advisories in the window. Selection and order are automatic: how stories are placed and ranked.