-
AI Security
AI Security 101: Where Each Attack Belongs and What Contains It
The mechanisms behind AI attacks have not changed since the spam filters of 2008. What changed is the blast radius.…
Read More » -
AI Governance and Policy
Why We Need a Chief AI Security Officer (CAISO)
With AI’s breakneck expansion, the distinctions between ‘cybersecurity’ and ‘AI security’ are becoming increasingly pronounced. While both disciplines aim to…
Read More » -
AI Security
Neural Trojans: Backdoors That Survive Safety Training
A backdoor is a specific trigger implanted in a model that stays dormant until it fires. The 2024 result that…
Read More » -
AI Security
Model Fragmentation Is Model Sprawl, and Nobody Has the Inventory
A quantised derivative of a model you scanned is a different artefact that you did not scan. Every variant carries…
Read More » -
AI Security
Model Evasion: Why Attackers Rarely Need Adversarial ML
Evasion research and evasion practice have been pointing in different directions for years. The attacks work in the lab, the…
Read More » -
AI Privacy
Homomorphic Encryption for ML: What the Overhead Buys
Homomorphic encryption lets an untrusted server compute on data it cannot read. The overhead is severe enough that the set…
Read More » -
AI Security
What 250 Poisoned Documents Actually Proved
Two hundred and fifty documents planted the same backdoor in models from 600M to 13B parameters. What it planted was…
Read More » -
AI Security
Semantic Adversarial Attacks: Leaving the Perturbation Budget Behind
A semantic attack changes the lighting, the hair colour or the phrasing. The result is enormous in pixel distance, obviously…
Read More » -
AI Safety and Alignment
The AI Alignment Problem
The AI alignment problem sits at the core of all future predictions of AI’s safety. It describes the complex challenge…
Read More » -
AI Perspectives
A (Very) Brief History of AI
As early as the mid-19th century, Charles Babbage and Ada Lovelace created the Analytical Engine, a mechanical general-purpose computer. Lovelace…
Read More » -
AI Security
When ML Bias Becomes a Security Failure
A demographic differential in false match rate is a demographic differential in exposure to impostors. NIST measured it in 2019…
Read More » -
AI Security
Adversarial Attacks on AI: What Has Actually Been Demonstrated
Adversarial examples are a real and unsolved property of trained models. Almost every famous demonstration of one attacking a deployed…
Read More » -
AI Disinformation
Introduction to AI-Enabled Disinformation
In recent years, the rise of artificial intelligence (AI) has revolutionized many sectors, bringing about significant advancements in various fields.…
Read More » -
AI Safety and Alignment
“Magical” Emergent Behaviours in AI: A Security Perspective
Emergent behaviours in AI have left both researchers and practitioners scratching their heads. These are the unexpected quirks and functionalities…
Read More » -
AI Privacy
Dynamic Data Masking Protects the View, Not the Model
Masking rewrites what a query returns and leaves the stored data alone. Whoever builds your training set either reads through…
Read More »
