arXiv:2603. 23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent.
arXiv:2606. 18430v1 Announce Type: new Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited.
arXiv:2607. 19430v1 Announce Type: cross Abstract: Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can smuggle instructions.
arXiv:2607. 06009v1 Announce Type: cross Abstract: Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need.
arXiv:2606. 28962v1 Announce Type: cross Abstract: Model quantization is essential for the efficient deployment of Large Language Models (LLMs), but introduces a critical vulnerability: Quantization-Conditioned Backdoor (QCB) attacks.
arXiv:2606. 04027v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autoregressive LLMs.
arXiv:2606. 12703v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) agents increasingly run with persistent memory that accumulates across user sessions.
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
arXiv:2606. 10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering.
arXiv:2602. 06911v2 Announce Type: replace-cross Abstract: As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks.
Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Existing guardrail methods, such as LLM-as-a-judge and cloud-based safety APIs are able to detect unsafe content.
arXiv:2608. 17556v1 Announce Type: cross Abstract: Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls.
arXiv:2606. 28479v1 Announce Type: cross Abstract: CSIRTs increasingly fine tune language models on vulnerability scan records, but these records expose internal network topology and create privacy risks under regulations such as GDPR and LGPD.