arXiv AI
Hidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 9
What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks
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 AI
Aug 24
Truth Lies Deep: Countering Semantic Camouflage via Latent Intent Verification
The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.
arXiv AI
Sep 30
Render Before Reading: Visual Rendering as a Prompt Injection Defense
The paper investigates how multimodal large language models are more susceptible to prompt injection when adversarial instructions are presented as text rather than as non-textual inputs like images. It proposes a training‑free defense that renders untrusted payloads into typographic images (or audio) before they reach the model, a method called Pictionary. Experiments on ten models and two benchmarks show that this approach significantly lowers attack success rates while maintaining normal functionality, and that fine‑tuning on image‑rendered instructions can further reduce the modality gap.
arXiv AI
Sep 23
Decoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection
arXiv:2609.24801v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in production systems, raising concerns about their exposure to adversarial manipulation throu...
arXiv Machine Learning
Jun 5
Steering Vectors are an Adversarial Attack Surface
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 Computation and Language
Sep 2
Can LLMs Reliably Self-Report Adversarial Prefills, and How?
The study investigates whether large language models (LLMs) can reliably detect when their own responses have been manipulated by adversarial prefill attacks. Across ten instruction‑tuned LLMs ranging from 3B to 70B parameters and four safety benchmarks, none consistently recognized compromised outputs, with models claiming intent on prefilled responses at an average of 25.3%. The research identifies that introspective signals mainly arise from safety reasoning and refusal, and that training to improve introspection can paradoxically increase attack success, underscoring the fragility of LLM self‑reporting in safety contexts.