Daily, Sunday 27 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
CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification
Neural code models have found widespread success in tasks pertaining to code intelligence, yet they are vulnerable to backdoor attacks, where an adversary can manipulate the victim model's behavior by inserting triggers into the source code. Recent studies indicate that…
- 2
Over 70 zero-day flaws get hackers $1 million at Pwn2Own Ireland
The fourth day of Pwn2Own Ireland 2024 marked the end of the hacking competition with more than $1 million in prizes for over 70 unique zero-day vulnerabilities in fully patched devices.
- 3
Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions
Large Language Models have introduced novel opportunities for text comprehension and generation. Yet, they are vulnerable to adversarial perturbations and data poisoning attacks, particularly in tasks like text classification and translation. However, the adversarial robustness…
Further reading, by topic
Advisories in this window
- 7 npm advisories7 moderate
- 1 Packagist advisory1 low
This edition
6 developments and 8 advisories in the window. Selection and order are automatic: how stories are placed and ranked.