arXiv:2607. 19396v1 Announce Type: new Abstract: Document-based LLM systems often flatten a PDF before guardrails inspect it.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2608. 00144v2 Announce Type: replace Abstract: Membership inference (MIA) on language models is usually summarised by aggregate ROC-AUC, but such evaluations are confounded: model-free blind baselines can separate members from non-members using surface text alone.
arXiv:2607. 09290v1 Announce Type: cross Abstract: In the digital era, Portable Document Format (PDF) is one of the most widely used file formats for storing and exchanging digital documents due to its platform independence and rich functionality.
arXiv:2608. 00144v1 Announce Type: new Abstract: Membership inference (MIA) on language models is usually summarised by an aggregate ROC-AUC, but such evaluations are confounded: model-free blind baselines separate members from non-members from surface text alone.
arXiv:2607. 02079v1 Announce Type: cross Abstract: We present HaloGuard 1.
arXiv:2608. 02678v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems are vulnerable to corpus poisoning: an attacker who inserts a crafted document into the retrieval corpus can steer the underlying large language model (LLM) toward an attacker-chosen wrong answer.
arXiv:2606. 02959v1 Announce Type: new Abstract: Published evaluations of prompt-injection and jailbreak detectors for Large Language Models often suffer from two systematic weaknesses: per-dataset threshold tuning and undisclosed operating points.