Daily, Friday 5 July 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
Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers
Large language models (LLMs) have acquired the ability to handle longer context lengths and understand nuances in text, expanding their dialogue capabilities beyond a single utterance. A popular user-facing application of LLMs is the multi-turn chat setting. Though longer chat…
- 2
Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs
Backdoors are hidden behaviors that are only triggered once an AI system has been deployed. Bad actors looking to create successful backdoors must design them to avoid activation during training and evaluation. Since data used in these stages often only contains information…
- 3
Establishing Provenance Before Coding: Traditional and Next-Gen Software Signing
Software engineers integrate third-party components into their applications. The resulting software supply chain is vulnerable. To reduce the attack surface, we can verify the origin of components (provenance) before adding them. Cryptographic signatures enable this. This…
Further reading, by topic
Advisories in this window
- 316 npm advisories316 critical
- 1 Go advisory1 moderate
This edition
6 developments and 317 advisories in the window. Selection and order are automatic: how stories are placed and ranked.