On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,982 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “trapdoors”

Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networkscs.LG

Trapdoors in neural networks attract adversarial attacks, making them easier to detect.

problem Adversarial attacks on neural networks are difficult to detect and defend against.

method Intentionally inject trapdoors to attract adversarial attacks, then detect them based on feature similarity.

result Trapdoor-protected models can accurately detect adversarial examples with minimal impact on normal classification.

adversarial attacks neural networks honeypots trapdoors feature similarity

2019-04-18abs ↗pdf ↗

Lower Bounds for Adversarially Robust PAC Learningcs.LG

This work studies PAC learning under evasion attacks, proving exponential sample complexity for high-dimensional inputs.

problem Formal study of PAC learning under evasion attacks where the adversary misclassifies perturbed samples.

method Proves exponential sample complexity for high-dimensional inputs under evasion attacks, formalizes hybrid attacks.

result PAC learning requires exponential sample complexity for high-dimensional inputs under evasion attacks.

PAC learning adversarial attacks sample complexity hybrid attacks evasion attacks

2019-06-13abs ↗pdf ↗