arXiv:2601. 17483v2 Announce Type: replace Abstract: Training modern neural networks is increasingly fragile, with rare but severe destabilizing updates often causing irreversible divergence or silent performance degradation.
arXiv:2606. 00539v1 Announce Type: new Abstract: Training stability is a key bottleneck in low-precision language model training: efficient low-cost paths can still produce short-lived numerical risks at a small set of operators.
arXiv:2606. 27694v1 Announce Type: cross Abstract: Randomized Smoothing (RS) provides rigorous robustness guarantees for neural networks without architectural constraints, yet its adoption is limited by extreme computational costs.
arXiv:2606. 10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering.
arXiv:2502. 17055v5 Announce Type: replace Abstract: Training instability in modern deep learning systems is frequently triggered by rare but extreme gradient-norm spikes, which can induce oversized parameter updates, corrupt optimizer state, and lead to slow recovery or divergence.
arXiv:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.
Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning through retraining or weight modification, which can be costly and may hurt task performance, or they use model-agnostic safety classifiers, which may miss failures specific to a given fine-tuned checkpoint.
The paper introduces Fed-ADR, a coordinated attack framework where a malicious orchestrator server directs heterogeneous adversarial clients to adapt their gradient updates in real time, thereby evading existing federated learning defenses and drastically reducing global model accuracy. It also presents a lightweight detection mechanism that estimates true client gradients from historical data to spot coordinated attacks, and an in-situ recovery method that restores model performance without restarting training. Experiments on MNIST, Fashion‑MNIST, and CIFAR‑10 show the attack can drop accuracy from over 90% to below 10%, while the defense can recover accuracy to above 90% within a few rounds at a computational cost at least 20× lower than retraining from scratch.
arXiv:2609.25962v1 Announce Type: new Abstract: Neural network verification has become a key tool for providing formal guarantees on the behaviour of neural networks. However, many verification probl...
arXiv:2606. 00400v1 Announce Type: new Abstract: Continual instruction tuning updates a language model through a sequence of new domains, yet each update can progressively erode previously learned capabilities and alignment behavior.
OVIG is an optimistic verification framework that audits AI training by replaying the process and comparing gradient differences against an empirically calibrated boundary. It treats any gradient difference exceeding this boundary as a malicious deviation. By partitioning training into stride‑s intervals and storing evidence only at interval endpoints, OVIG dramatically reduces off‑chain storage and transmission costs while maintaining zero attack success rate across language, vision, and diffusion workloads.
arXiv:2606. 25151v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) embed governing equations in their loss function, enabling mesh-free solutions to partial differential equations.
The paper introduces Open-1B, a language model trained under a new fully auditable regime that ensures every training operation is reproducible on heterogeneous commodity hardware with bitwise certainty. By enforcing a fixed order on sources of nondeterminism—GPU reductions, data batch ordering, and inter/intra-node communication—the authors enable auditors to replay and verify individual training steps on a single machine. The release includes the full pretraining dataset, all intermediate checkpoints, the training codebase, and an audit harness for step-by-step verification.