Prismata cuts web-agent prompt-injection attack success from 85.5% to 0.7% via Biba-inspired DOM trust labeling and mechanical least-privilege confinement without site annotations.
FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts , booktitle =
6 Pith papers cite this work, alongside 37 external citations. Polarity classification is still indexing.
6
Pith papers citing it
37
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
A new 507-leaf taxonomy and 4x6 Target x Technique matrix audits six LLM attack benchmarks and finds they cover at most 25% of the threat surface with entire STRIDE categories untested.
UJEM-KL improves cross-model transferability of untargeted jailbreaks on VLMs by maximizing entropy at decision tokens rather than enforcing fixed response patterns.
Degraded image resolution in MLLMs bypasses safety alignments via cognitive overload, raising jailbreak rates across perturbations.
Comic-based visual narratives achieve over 90% ensemble success rates on multiple MLLMs, outperforming text and random-image baselines while breaking existing safety methods and evaluators.
Adaptive probe-based steering guided by model extraction and activation statistics improves LLM jailbreak success rates from 6% to 70% average harmfulness without extra contrastive prompts or manual tuning.
citing papers explorer
-
Prismata: Confining Cross-Site Prompt Injection in Web Agents
Prismata cuts web-agent prompt-injection attack success from 85.5% to 0.7% via Biba-inspired DOM trust labeling and mechanical least-privilege confinement without site annotations.
-
Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks
A new 507-leaf taxonomy and 4x6 Target x Technique matrix audits six LLM attack benchmarks and finds they cover at most 25% of the threat surface with entire STRIDE categories untested.
-
Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization
UJEM-KL improves cross-model transferability of untargeted jailbreaks on VLMs by maximizing entropy at decision tokens rather than enforcing fixed response patterns.
-
Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment
Degraded image resolution in MLLMs bypasses safety alignments via cognitive overload, raising jailbreak rates across perturbations.
-
Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
Comic-based visual narratives achieve over 90% ensemble success rates on multiple MLLMs, outperforming text and random-image baselines while breaking existing safety methods and evaluators.
-
Adaptive Probe-based Steering for Robust LLM Jailbreaking
Adaptive probe-based steering guided by model extraction and activation statistics improves LLM jailbreak success rates from 6% to 70% average harmfulness without extra contrastive prompts or manual tuning.