Editorial desk
AI Attacks Editorial
AI Attacks Editorial is the publishing identity for AI Attacks. It is a desk, not a person: no named author, no biography, no professional certifications.
Articles published under this byline are researched from primary sources — vendor and project documentation, published standards and specifications, research papers, and measurements published by whoever took them — drafted with AI assistance, and edited against those cited sources before publication. Nothing here is based on first-hand testing in a private lab, and any figure that appears is attributed to the source it came from.
Corrections go to hello@aiattacks.dev. More detail is on the about page and the editorial disclosure.
Posts (21)
- Attack Techniques
How Indirect Prompt Injection Works
How indirect prompt injection works: attacker instructions hidden in web pages, emails and RAG documents, the attack surface, and what defenders can do.
- Defense
LLM Jailbreak Defenses: Why Static Filters Fail
Why LLM jailbreak defenses that score well on static benchmarks collapse against adaptive attackers, and what an honest robustness evaluation has to measure.
- Attack Techniques
LLM Jailbreak Examples: 10 Documented Patterns
Ten LLM jailbreak examples drawn from published research, with the reported success rates, the mechanism behind each, and the signals that detect them.
- Explainer
Prompt Injection vs Jailbreak: How They Differ and Why It Matters
Prompt injection targets your application architecture; jailbreaking targets the model's safety alignment. Confusing them defends the wrong layer.
- Defense
How to Detect Prompt Injection: Four Approaches Ranked
Input heuristics, classifier APIs, hidden-state probes, and output monitoring: how to detect prompt injection in production LLM apps, with tradeoffs.
- Explainer
Adversarial Examples Explained Simply: How Pixels Fool a Model
A plain-language walkthrough of adversarial examples: what they are, why neural networks fall for them, how FGSM works, and what defenders can do.
- LLM Security
OWASP Top 10 LLM Explained: Every Entry and What to Fix
The OWASP Top 10 for LLM Applications 2025 explained: every entry, what it means in production, what the revision changed, and which fixes return most.
- Adversarial ML
Evasion Attacks on Production Classifiers: Malware, Spam, Fraud
Deployed ML classifiers in malware, spam, and fraud detection face evasion attacks where the attacker has a clear payoff.
- Adversarial ML
Poisoning Web-Scale Training Sets: Split-View and Frontrunning
You don't need to control a model's training pipeline to poison it — you only need to control content the crawler will fetch.
- Adversarial ML
Adversarial Examples Against Vision Models in 2026
Where physical-world adversarial patches and digital attacks stand against modern vision models, what has been hardened, and what red teams should test.
- Attack Techniques
Adversarial Suffixes: A GCG Practitioner Guide
A working guide to Greedy Coordinate Gradient search: how it finds adversarial suffixes that bypass alignment, and what the transferability result means.
- Attack Patterns
Jailbreaking Multimodal Models: Visual Prompt Injection Attacks
How attackers use images, typography, and adversarial perturbations to bypass safety guardrails in multimodal models, and why vision widens the surface.
- Attack Patterns
LLM Context Window Poisoning
How attackers plant persistent malicious instructions in memory and context, survive summarization, and carry influence across separate LLM sessions.
- Attack Patterns
Indirect Prompt Injection in RAG Pipelines
How attackers embed malicious instructions in documents that get retrieved into LLM context — and why RAG makes prompt injection a supply-chain problem.
- Attack Techniques
Many-Shot Jailbreaking: What the Research Shows
How hundreds of synthetic compliance examples in a long-context prompt erode safety training, what the published results show, and why patching is hard.
- Adversarial ML
Model Extraction via Black-Box Query Attacks
How attackers reconstruct model behavior and decision boundaries through query-only access, the economics of the attack, and what stolen models enable.
- Adversarial ML
Model Inversion and Membership Inference: Extracting LLM Data
How membership inference reveals whether specific data trained a model, and how inversion reconstructs private text from gradients and model outputs.
- Attack Patterns
Supply Chain Attacks on AI Models: Poisoning and Backdoors
How attackers compromise models before production through dataset poisoning, malicious fine-tuning, and serialization exploits, and how to detect it.
- Attack Patterns
Tool-Call Hijacking in Agentic Systems
How attackers exploit the gap between LLM reasoning and function execution to trigger unauthorized tool calls, and why confirmation gaps are the root.
- Adversarial ML
Training Data Poisoning and Backdoor Attacks on LLMs
A technical deep dive into how adversaries manipulate training datasets and plant hidden backdoors in LLMs, covering triggers, stealth, and detection.
- Red Team
Building a CI Gate for Prompt Injection Regression
A practical CI gate that catches prompt injection regressions before release, so a routine prompt change cannot silently weaken your guardrails.