arXiv:2602.05066v1 Announce Type: new Abstract: As AI agents automate critical workloads, they remain vulnerable to indirect prompt injection (IPI) attacks. Current defenses rely on monitoring protocols that jointly evaluate an agent’s Chain-of-Thought (CoT) and tool-use actions to ensure alignment with user intent. We demonstrate that these monitoring-based defenses can be bypassed via a novel Agent-as-a-Proxy attack, where prompt injection attacks treat the agent as a delivery mechanism, bypassing both agent and monitor simultaneously. While prior work on scalable […]

Ver mais

In the current AI boom, the spotlight is almost exclusively on securing the latest GPUs. Hardware availability matters, but access to chips is only one variable in building large-scale infrastructure. As someone who has overseen deployments across 29 data centers on three continents, I’ve learned that procurement is only the visible part of the iceberg. The real complexity lies in the gap between hardware design and infrastructure reality. Modern GPU systems are increasingly designed for extremely high rack […]

Ver mais

Release: datasette-ports 0.3 A small update for my tool for helping me figure out what all of the Datasette instances on my laptop are up to. Show working directory derived from each PID Show the full path to each database file Output now looks like this: http://127.0.0.1:8007/ – v1.0a26 Directory: /Users/simon/dev/blog Databases: simonwillisonblog: /Users/simon/dev/blog/simonwillisonblog.db Plugins: datasette-llm datasette-secrets http://127.0.0.1:8001/ – v1.0a26 Directory: /Users/simon/dev/creatures Databases: creatures: /tmp/creatures.db Tags: datasette

Ver mais

arXiv:2603.20325v1 Announce Type: new Abstract: Deep learning models have achieved strong performance in medical image analysis, but their internal decision processes remain difficult to interpret. Concept Bottleneck Models (CBMs) partially address this limitation by structuring predictions through human-interpretable clinical concepts. However, existing CBMs typically overlook the contextual dependencies among concepts. To address these issues, we propose an end-to-end interpretable framework emph{DCG-Net} that integrates multimodal alignment with structured concept reasoning. DCG-Net introduces a Dual Cross-Attention module that replaces cosine […]

Ver mais

arXiv:2603.09980v1 Announce Type: new Abstract: LLM unlearning is essential for mitigating safety, copyright, and privacy concerns in pre-trained large language models (LLMs). Compared to preference alignment, it offers a more explicit way by removing undesirable knowledge characterized by specific unlearning datasets. In previous works, gradient ascent (GA) and its variants have shown promise for implementing unlearning, yet their untargeted nature results in unintended degradation of general capabilities, incomplete removal of knowledge, and the generation of incoherent responses, among […]

Ver mais

arXiv:2602.06155v1 Announce Type: cross Abstract: Diffusion models rely on a high-dimensional latent space of initial noise seeds, yet it remains unclear whether this space contains sufficient structure to predict properties of the generated samples, such as their classes. In this work, we investigate the emergence of latent structure through the lens of confidence scores assigned by a pre-trained classifier to generated samples. We show that while the latent space appears largely unstructured when considering all noise realizations, restricting […]

Ver mais

arXiv:2601.18932v1 Announce Type: cross Abstract: Popularized by their strong image generation performance, diffusion and related methods for generative modeling have found widespread success in visual media applications. In particular, diffusion methods have enabled new approaches to data compression, where realistic reconstructions can be generated at extremely low bit-rates. This article provides a unifying review of recent diffusion-based methods for generative lossy compression, with a focus on image compression. These methods generally encode the source into an embedding and […]

Ver mais

Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-distribution states due to compounding errors during deployment. We show that reusing the training data during inference via a semi-parametric retrieval-based imitation learning approach can alleviate this challenge. We present Difference-Aware Retrieval Policies for Imitation Learning (DARP), a semi-parametric retrieval-based imitation learning approach that addresses this limitation by reparameterizing the imitation learning problem in terms of local neighborhood structure rather than direct state-to-action mappings. Instead of […]

Ver mais

This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients’ training data are not independent and identically distributed. We propose a heuristic algorithm that uses server learning and client update filtering in combination with geometric median aggregation. We demonstrate via experiments that this approach can achieve significant improvement in model accuracy even when the fraction of malicious clients is high, even more than $50%$ in some cases, […]

Ver mais