Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation proposes a method to formally certify that disabling a specific circuit in a neural network removes a targeted skill while preserving another, for every input within a continuous region. The approach extends beyond testing by providing sound guarantees over continuous embedding-space regions, demonstrated on toy ReLU networks and a standard transformer. It also shows that no finite deterministic black-box test can guarantee removal, highlighting the necessity of formal verification.
arXiv:2609.26112v1 Announce Type: new Abstract: Mechanistic interpretability reverse-engineers transformer circuits one input at a time, leaving observed mechanisms without guarantees over bounded in...
arXiv:2605. 24033v2 Announce Type: replace Abstract: Mechanistic interpretability typically discovers circuits and then argues what they do from examples and ablations.
arXiv:2609.15533v1 Announce Type: cross Abstract: Mechanistic interpretability has become the dominant lens for understanding frontier language models, as their inner workings are complex and inheren...
The paper investigates how tokenization can undermine post‑release guarantees that sensitive knowledge has been edited or unlearned from open‑weight large language models. By showing that alternative valid tokenizations can bypass localized modifications, the authors introduce Toketive, a reference‑free attack that detects modified knowledge and reconstructs pre‑edit responses using only the released model. Experiments on five LLMs, six datasets, and six editing techniques reveal that 38.6% of alternative tokenizations recover suppressed information, with Toketive achieving high detection and reconstruction accuracy.
arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.
arXiv:2606. 13705v1 Announce Type: cross Abstract: Yes.
arXiv:2606. 23858v1 Announce Type: cross Abstract: A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network (NN) to misclassify.
arXiv:2606. 31653v1 Announce Type: cross Abstract: Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on the worst-case loss over an allowed perturbation set.
arXiv:2606. 29951v1 Announce Type: new Abstract: Interpretable Mesomorphic Neural Networks (IMNs) offer a promising framework that combines the predictive power of deep neural networks with the interpretability of linear models.
arXiv:2609.05794v1 Announce Type: cross Abstract: Open-weight large language models face a low-cost white-box threat from representation engineering attacks. Attackers can estimate refusal directions...
MeMark introduces a watermarking scheme for Spiking Neural Networks that embeds a multi‑bit identifier directly into the membrane state of selected Leaky Integrate‑and‑Fire neurons, rather than in the output head. The watermark is recoverable by comparing neuron firing thresholds, eliminating the need for a learned decoder. Experiments on various SNN architectures—including a 215.4M‑parameter SpikeGPT checkpoint—show that all 20 independent 64‑bit keys reliably pass verification under a 51/64 rule, remain robust after fine‑tuning, pruning, quantization, and output‑head replacement, and are not recovered by random keys or adaptive attacks within the tested threat model.
arXiv:2605. 03058v2 Announce Type: replace-cross Abstract: A central goal of explainable AI is to express large language model (LLM) decision logic symbolically and ground it in internal mechanisms.