arXiv:2606. 27287v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to screen and rank job applicants, creating incentives for candidates to strategically manipulate algorithmic hiring systems.
arXiv:2608. 08027v1 Announce Type: cross Abstract: Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or external data.
arXiv:2610.07723v1 Announce Type: cross Abstract: Safety alignment in Large Language Models (LLMs) remains vulnerable to backdoor attacks. Existing LLM backdoors are almost all input-centric: activat...
The paper investigates prompt injection attacks on Jev, a non‑generative decision model, using 510 reconstructed cases. It finds that malicious prompts can shift Jev’s action probabilities, though rarely cause it to choose the attacker’s target. Techniques such as override markers mitigate influence, while adaptive attacks that use score feedback roughly double the highest attacker‑target probability and increase success rates on new validation calls from 1.8% to 3.5%.
Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deployment puts the model through orders of magnitude more interactions than any evaluation...
arXiv:2606. 24381v1 Announce Type: cross Abstract: Prompt-based interaction has become a dominant paradigm for using large language models (LLMs), where multiple candidate prompts are evaluated and the top-ranked one is selected for downstream use.
The paper demonstrates that large language model (LLM) evaluators, whether reward‑model based or prompted LLM‑as‑a‑Judge, exhibit significant language bias in multilingual settings. Experiments with semantically identical instruction‑response pairs across 23 languages reveal that lower‑resource languages receive higher scores, a bias that persists across eight open‑weight evaluators and is not detectable by standard pairwise accuracy metrics. The authors link the bias to model uncertainty and language identity, showing it cannot be explained by content difficulty alone.
The paper introduces a prompt‑injection detection framework for email assistants that models attacks as a chain of stages. It combines a text detector, stage‑specific verifiers, rule‑based risk signals, user intent consistency checks, and a logistic decision policy. Experiments on five benchmarks show the framework outperforms pretrained detectors, achieving a mean F1 of 0.406 versus 0.216, and demonstrate that training on benign emails resembling attacks reduces false alarms.
arXiv:2512. 08724v3 Announce Type: replace Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age.
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. 18530v1 Announce Type: cross Abstract: Domain-camouflaged injection attacks embed malicious instructions in retrieved content using domain-appropriate vocabulary, evading standard detectors that rely on syntactic injection markers.
arXiv:2608.31105v1 Announce Type: new Abstract: Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deployment puts the model through orders of...
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. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.