Adversarial Logic

Supply Chain Security 30 Jun 2026 21 min read

Vetting the Black Box: A Supply Chain Due Diligence Framework for AI and ML

In March 2026, a poisoned LiteLLM release sat live on PyPI for 40 minutes; long enough to reach three million downloads. The publisher was trusted. The artifact was not. Most AI teams have a process for neither. This article provides one.

LLM Jailbreaks & Defenses 13 May 2026 11 min read

Perplexity Filtering: The First LLM Defense (And Why Evolutionary Attacks Broke It)

In the previous post on evolutionary jailbreaking, I noted that GCG suffixes are “trivially detectable by any perplexity filter.” That line hides an entire chapter of the LLM

LLM Jailbreaks & Defenses 19 Apr 2026 12 min read

Evolving the Jailbreak: How Genetic Algorithms Are Defeating LLM Safety

In July 2023, Zou et al. published a paper that broke open the field of automated LLM jailbreaking [1]. Their method, Greedy Coordinate Gradient (GCG), appends an optimized

LLM Jailbreaks & Defenses 12 Apr 2026 13 min read

Swarm Intelligence as a Weapon: How Nature-Inspired Algorithms Attack Neural Networks

In a previous post, I covered the one-pixel attack, where differential evolution finds a single pixel change that fools an image classifier. DE is effective, but it’

Reinforcement Learning Security 26 Mar 2026 14 min read

AI Will Cheat to Win: Reward Hacking from 1994 to 2025

In February 2025, Palisade Research set up hundreds of chess matches between seven large language models and Stockfish, a top-tier open-source chess engine [1]. The models

Supply Chain Security 17 Mar 2026 14 min read

The AI Agent Supply Chain Is Vulnerable. You Probably Are Too.

On September 8, 2025, a phishing email impersonating npm support hit the inbox of Josh Junon, maintainer of chalk, debug, and other foundational JavaScript packages. Within hours, attackers

Adversarial Optimization 18 Feb 2026 17 min read

One-Pixel Attacks: Why Computer Vision Security Is Broken

State-of-the-art image classifiers can identify thousands of objects with near-human accuracy. They power self-driving cars, medical diagnostics, and security systems. But a 2019

LLM Jailbreaks & Defenses 28 Jan 2026 9 min read

GPT-OSS Safeguard: What It Actually Does (And Common Mistakes to Avoid)

GPT-OSS Safeguard isn't just "Llama Guard but from OpenAI." It's a policy-following reasoning model - you write the safety rules, it interprets them at inference time. That flexibility is powerful for custom policies, but deploy it wrong and you'll be out of compute fast.

LLM Jailbreaks & Defenses 24 Jan 2026 8 min read

Llama Guard: What It Actually Does (And Doesn't Do)

Llama Guard isn't a firewall. It's not antivirus for your prompts. And if you're treating it like either, you're probably leaving gaps in your AI security.