Daily, Wednesday 19 October 2022
Reconstructed on 20 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
Not All Poisons are Created Equal: Robust Training against Data Poisoning
Data poisoning causes misclassification of test time target examples by injecting maliciously crafted samples in the training data. Existing defenses are often effective only against a specific type of targeted attack, significantly degrade the generalization performance, or…
- 2
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of a large-scale Pre-trained Language Model (PLM) with poisoned samples. Although the clean weights of PLMs…
- 3
Critical RCE Vulnerability Discovered in Popular Cobalt Strike Hacking Software
HelpSystems, the company behind the Cobalt Strike software platform, has released an out-of-band security update to address a remote code execution vulnerability that could allow an attacker to take control of targeted systems. Cobalt Strike is a commercial red-team framework…
Further reading, by topic
Advisories in this window
- 3 Packagist advisories3 moderate
- 3 npm advisories1 critical · 2 high
- 2 Go advisories2 high
- 1 NuGet advisory1 moderate
- 1 PyPI advisory1 high
- 1 Maven advisory1 critical
This edition
8 developments and 11 advisories in the window. Selection and order are automatic: how stories are placed and ranked.