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 10 of 2024 · Retrospective · Covers 27 February 2024 12:00 to 5 March 2024 12:00 UTC

Read on the web

Top developments

Lazarus hackers exploited Windows zero-day to gain Kernel privileges

BleepingComputer · Incident · Remediation

Defend against human-operated ransomware attacks with Microsoft Copilot for Security

Microsoft · Incident · Agentic SDLC

LLM Prompt Injection Worm

Schneier on Security · Research · AI Security

SAST

VulMCI : Code Splicing-based Pixel-row Oversampling for More Continuous Vulnerability Image Generation

arXiv · Research · SAST

SCA

DevPhish: Exploring Social Engineering in Software Supply Chain Attacks on Developers

arXiv · Research · SCA

Lazarus Exploits Typos to Sneak PyPI Malware into Dev Systems

The Hacker News · Analysis · SCA

Enhance container software supply chain visibility through SBOM export with Amazon Inspector and QuickSight

AWS Security Blog · Analysis · SCA

DAST

Penetration Testing of 5G Core Network Web Technologies

arXiv · Research · DAST

Kali Linux 2024.1 released: New tools, new look, new Kali Nethunter kernels

Help Net Security · Release · DAST

Agentic SDLC

Who Am I? Conditional Prompt Injection Attacks with Microsoft Copilot

Embrace The Red · Analysis · Agentic SDLC, AI Security

Microsoft Secure: Learn expert AI strategy at our online event

Microsoft · Analysis · Agentic SDLC

AI-BOM

Our response to the US Army’s RFI on developing AIBOM tools

Trail of Bits · Analysis · AI-BOM

Remediation

Ivanti integrity checker tool needs latest update to work, Five Eyes alert warns

CyberScoop · Analysis · Remediation

Trust

Secure by Design: Google’s Perspective on Memory Safety

Google · Analysis · Trust

Models

Precise Extraction of Deep Learning Models via Side-Channel Attacks on Edge/Endpoint Devices

arXiv · Research · Models

Robustness bounds on the successful adversarial examples in probabilistic models: Implications from Gaussian processes

arXiv · Research · Models

WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection

arXiv · Research · Models

Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models

arXiv · Research · Models

AI Security

Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications

arXiv · Research · AI Security

InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

arXiv · Research · AI Security

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

arXiv · Research · AI Security

Advisories in this window

  • 21 Go advisories · 2 critical · 7 high · 7 moderate · 5 low
  • 16 PyPI advisories · 1 critical · 3 high · 12 moderate
  • 15 npm advisories · 7 critical · 2 high · 5 moderate · 1 low
  • 11 Packagist advisories · 10 moderate · 1 low
  • 10 Maven advisories · 5 high · 5 moderate
  • 8 RubyGems advisories · 5 moderate · 3 low
  • 1 crates.io advisory · 1 high
  • 1 NuGet advisory · 1 moderate
  • 1 Swift advisory · 1 high

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.