Daily, Tuesday 28 November 2023
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
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training. However, they are vulnerable to backdoor attacks as reported by recent studies. When a data input (e.g.,…
- 2
How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
This work focuses on the potential of Vision LLMs (VLLMs) in visual reasoning. Different from prior studies, we shift our focus from evaluating standard performance to introducing a comprehensive safety evaluation suite, covering both out-of-distribution (OOD) generalization…
- 3
Experts Uncover Passive Method to Extract Private RSA Keys from SSH Connections
A new study has demonstrated that it's possible for passive network attackers to obtain private RSA host keys from a vulnerable SSH server by observing when naturally occurring computational faults that occur while the connection is being established. The Secure Shell (SSH)…
Advisories in this window
- 10 Go advisories9 moderate · 1 low
- 6 Packagist advisories2 high · 4 moderate
- 5 PyPI advisories5 moderate
- 2 npm advisories1 moderate · 1 low
- 2 Maven advisories2 moderate
This edition
13 developments and 25 advisories in the window. Selection and order are automatic: how stories are placed and ranked.