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.
SpecGuard is an inference‑time backdoor detector that leverages speculative decoding—using a small draft model to propose tokens and a target model to verify them—without adding extra model computation. By monitoring the draft‑token acceptance rate, SpecGuard detects when a target model shifts toward attacker‑controlled behavior while the draft model does not, signaling a backdoor trigger. The method reliably identifies a range of backdoor types, including stealthy attacks that bypass input‑level filters, across multiple model families.
arXiv:2609.22818v1 Announce Type: cross Abstract: Memory-poisoning defenses for LLM agents are typically evaluated by their ability to prevent attacks. However, the traffic they process is rarely adv...
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.
Guardrail models, which screen malicious prompts in LLM services, often use lightweight Transformers with short context windows and bucketed positional encodings. The study identifies a new failure mode called Overflip, where repeating a prompt causes the guardrail’s prediction to flip from malicious to benign as the sequence length increases. Experiments on nine popular guardrails show that 5 models exhibit MAL→BEN flips on 100 prompts, with flip rates ranging from 8% to 92% and first flips occurring between 2.6k and 9.4k tokens, highlighting a gradual attention dispersion distinct from traditional attention‑dilution attacks.