Daily, Monday 20 October 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
Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can the unlearning process itself be backdoored, appearing…
- 2
Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
Adversarial attacks by malicious users that threaten the safety of large language models (LLMs) can be viewed as attempts to infer a target property $T$ that is unknown when an instruction is issued, and becomes knowable only after the model's reply is observed. Examples of…
- 3
BreakFun: Jailbreaking LLMs via Object Instantiation under Simulated Code Execution
Large Language Models (LLMs) are widely used because they process structures, syntax and code well, but this same ability also makes them paradoxically vulnerable. We introduce BreakFun, a jailbreak method that frames a harmful request as code-execution simulation. The prompt…
Further reading, by topic
Models
- 4
- 5
This edition
6 developments and 0 advisories in the window. Selection and order are automatic: how stories are placed and ranked.