arXiv:2606. 08403v1 Announce Type: cross Abstract: Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views.
arXiv:2601. 22818v2 Announce Type: replace-cross Abstract: Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels.
arXiv:2606. 09411v1 Announce Type: cross Abstract: Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs.
arXiv:2606. 09135v1 Announce Type: cross Abstract: We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions.
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:2604. 06247v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) are vulnerable to jailbreaks and prompt injections delivered through text or images.
arXiv:2608. 01043v2 Announce Type: replace-cross Abstract: We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models (VLMs): pairing an encoded jailbreak prompt with an unrelated decoy image can sharply lower attack success rate (ASR).
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:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.
arXiv:2608. 14697v1 Announce Type: new Abstract: Steganography in large language models offers a way to embed hidden messages within natural-sounding text.
arXiv:2606. 09700v1 Announce Type: cross Abstract: Large language model (LLM)-powered content moderation systems have become a critical defense against harmful online content.
arXiv:2608. 07808v1 Announce Type: cross Abstract: Four years after prompt injection was first identified in 2022, attacks are still predominantly documented as verbatim strings rather than structured exploits, despite advancing agent capabilities and threat actors embedding injections to subvert AI-assisted security analysis.
arXiv:2608. 10279v1 Announce Type: cross Abstract: Streaming language-model output creates a release-timing problem: complete-response moderation acts after streamed text has escaped, whereas repeated semantic classification of partial text can be costly and unstable.