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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “class-oriented”

Towards Class-Oriented Poisoning Attacks Against Neural Networkscs.LG

Paper introduces class-oriented poisoning attacks to improve adversarial availability attacks.

problem Improving adversarial availability attacks on neural networks.

method Gradient-based framework for crafting poisoned images at the class level.

result Demonstrated effectiveness of class-oriented poisoning attacks on various models and datasets.

poisoning attacks neural networks class-oriented availability attacks backdoor attacks

2020-07-31abs ↗pdf ↗

A new proof of Milnor-Wood inequalitymath.GT

New proof of Milnor-Wood inequality for circle bundles.

problem Proving the Milnor-Wood inequality for circle bundles.

method Using a local formula to compute the Euler class from the singularities of a quasisection, and sketching two other proofs.

result A new proof of the Milnor-Wood inequality.

Milnor-Wood inequality circle bundles Euler class orientable surfaces genus

2024-12-19abs ↗pdf ↗

Iterative Causal Discovery: Per-Edge Impossibility Certificates, Tier-Aware Oracle Queries, and the

1+K

Lower Boundstat.ML

New protocol identifies impossible edge orientations in causal graphs.

problem Causal-discovery algorithms cannot distinguish edge directions without assumptions.

method Discrete impossibility certificates and oracle queries.

result Upper bound of

1+K

expert interactions for DAG recovery.

causal discovery impossibility certificates oracle queries upper bound Markov equivalence class

2026-05-26abs ↗pdf ↗