the
∞
.ai
Search
/
Concepts
trail ·
0 nodes
Every concept
Adversarial
8 concepts, 8 reviewed and merged.
Alignment
Jailbreak
A prompt that talks a model out of its own guardrails.
verified
Attacks
Backdoor Attack
A backdoored model behaves correctly on everything you test and misbehaves on inputs carrying a specific trigger — a…
verified
Data Poisoning
If a model trains on data scraped from the open web, anyone who can write to the web can contribute to the training…
verified
Evaluation
Red Teaming
Attack your own system before someone else does.
verified
Foundations
Adversarial Example
Change an image by an amount no person can see, and a classifier that was right becomes confidently wrong.
verified
Certified Robustness
Empirical defences are claims that nobody has broken them yet, and the history of the field is a list of such claims…
verified
Methods
Adversarial Training
If a model fails on inputs an attacker constructs, train it on those inputs.
verified
Regimes
Robustness-Accuracy Tradeoff
Robust models are less accurate on clean data, and not because anyone has been careless.
verified