Daily, Monday 17 March 2025
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
Fake "Security Alert" issues on GitHub use OAuth app to hijack accounts
A widespread phishing campaign has targeted nearly 12,000 GitHub repositories with fake "Security Alert" issues, tricking developers into authorizing a malicious OAuth app that grants attackers full control over their accounts and code.
- 2
D-ADD: An Effective Plug-In for Defending Against Model Stealing
Malicious users attempt to replicate commercial models functionally at low cost by training a clone model with query responses. Timely prevention of such model-stealing attacks is challenging, as it requires achieving robust protection, maintaining utility, and ensuring low…
- 3
A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learning
Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a closer look at the optimization objective of adversarial trigger learning and propose ATLA:…
Advisories in this window
- 1 Maven advisory1 moderate
- 1 Go advisory1 moderate
This edition
5 developments and 2 advisories in the window. Selection and order are automatic: how stories are placed and ranked.