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 52 of 2023 · Retrospective · Covers 19 December 2023 12:00 to 26 December 2023 12:00 UTC

Read on the web

Top developments

Google fixes 8th Chrome zero-day exploited in attacks this year

BleepingComputer · Incident · Remediation

OpenAI Begins Tackling ChatGPT Data Leak Vulnerability

Embrace The Red · Incident · AI Security

Ivanti releases patches for 13 critical Avalanche RCE flaws

BleepingComputer · Advisory · Remediation

SAST

Catching OpenSSL misuse using CodeQL

Trail of Bits · Analysis · SAST

DAST

HeisenTrojans: They Are Not There Until They Are Triggered

arXiv · Research · DAST

Agentic SDLC

Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

arXiv · Research · Agentic SDLC, AI Security

Remediation

OpenVEX and Open Source Vulnerability Scanners: How the Dynamic Duo Improves Vulnerability Management

OpenSSF · Analysis · Remediation, Trust

Xfinity waited to patch critical Citrix Bleed 0-day. Now it’s paying the price

Ars Technica: Security · Analysis · Remediation

LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks

arXiv · Research · Remediation

Trust

CISA seeking comments on its ‘secure by design’ guidance

CyberScoop · Standard / policy · Trust

Models

Reinforcement Unlearning

arXiv · Research · Models

Punctuation Matters! Stealthy Backdoor Attack for Language Models

arXiv · Research · Models

Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It

arXiv · Research · Models

MEAOD: Model Extraction Attack against Object Detectors

arXiv · Research · Models

AI Security

Recommendations to help mitigate prompt injection: limit the blast radius

Simon Willison · Analysis · AI Security

Data Exfiltration Using Indirect Prompt Injection

Schneier on Security · Analysis · AI Security

Advisories in this window

  • 16 npm advisories · 15 critical · 1 moderate
  • 15 PyPI advisories · 2 critical · 6 high · 6 moderate · 1 low
  • 7 Maven advisories · 1 critical · 3 high · 3 moderate
  • 6 Packagist advisories · 1 high · 4 moderate · 1 low
  • 6 Go advisories · 4 high · 2 moderate
  • 2 crates.io advisories · 2 moderate
  • 1 NuGet 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.