PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address.

Keryn Headlines

Weekly, week 43 of 2024 · Retrospective · Covers 15 October 2024 11:00 to 22 October 2024 11:00 UTC

Read on the web

Top developments

SolarWinds Web Help Desk flaw is now exploited in attacks

BleepingComputer · Incident · Remediation

GitHub patches critical vulnerability in its Enterprise Servers

CyberScoop · Analysis · Remediation

Sabotage evaluations for frontier models

Anthropic · Research · Models

Malicious npm Packages Target Developers' Ethereum Wallets with SSH Backdoor

The Hacker News · Research · SCA

SAST

From Solitary Directives to Interactive Encouragement! LLM Secure Code Generation by Natural Language Prompting

arXiv · Research · SAST

SCA

CVE-2024-9537: ScienceLogic SL1 Unspecified Vulnerability added to CISA's Known Exploited Vulnerabilities catalog

CISA · Advisory · SCA

Dirty-Waters: Detecting Software Supply Chain Smells

arXiv · Research · SCA

DAST

Adding web pentesting functionality to PTHelper

arXiv · Research · DAST, Trust

Guide: The Ultimate Pentest Checklist for Full-Stack Security

The Hacker News · Guide · DAST

Remediation

Microsoft Reveals macOS Vulnerability that Bypasses Privacy Controls in Safari Browser

The Hacker News · Analysis · Remediation

North Korean ScarCruft Exploits Windows Zero-Day to Spread RokRAT Malware

The Hacker News · Analysis · Remediation

VMware Releases vCenter Server Update to Fix Critical RCE Vulnerability

The Hacker News · Analysis · Remediation

Hackers Exploit Roundcube Webmail XSS Vulnerability to Steal Login Credentials

The Hacker News · Analysis · Remediation

Trust

How Do AI Companies "Fine-Tune" Policy? Examining Regulatory Capture in AI Governance

arXiv · Research · Trust

Coalition for Secure AI Forms Technical Steering Committee to Advance AI Security Workstreams

CoSAI · Analysis · Trust

170 AWS services achieve HITRUST certification

AWS Security Blog · Analysis · Trust

Models

Bayesian scaling laws for in-context learning

arXiv · Research · Models

Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis

arXiv · Research · Models

Designing Robust Cyber-Defense Agents with Evolving Behavior Trees

arXiv · Research · Models

An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks

arXiv · Research · Models

AI Security

This prompt can make an AI chatbot identify and extract personal details from your chats

Simon Willison · Analysis · AI Security

Jailbreaking and Mitigation of Vulnerabilities in Large Language Models

arXiv · Research · AI Security, Models

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment

arXiv · Research · AI Security

Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models

arXiv · Research · AI Security, Models

Advisories in this window

  • 131 npm advisories · 124 critical · 4 high · 1 moderate · 2 low
  • 6 Go advisories · 2 critical · 1 high · 3 moderate
  • 6 PyPI advisories · 1 critical · 2 high · 3 moderate
  • 5 Maven advisories · 1 critical · 2 high · 2 moderate
  • 4 RubyGems advisories · 4 moderate
  • 3 Packagist advisories · 1 high · 1 moderate · 1 low
  • 3 NuGet advisories · 1 high · 2 moderate
  • 1 Pub advisory · 1 high
  • 1 crates.io advisory · 1 moderate

All advisories

Titles, links and short excerpts only; every item links to its source. Selection is automatic; the editor's note is AI-drafted and checked as described. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.