Pith. sign in

Robo-troj: Attacking llm-based task planners

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CR 2

years

2026 1 2025 1

roles

background 1

polarities

background 1

representative citing papers

CacheTrap: Unveiling a Stealthier Gray-Box Trojan against LLMs

cs.CR · 2025-11-27 · conditional · novelty 8.0

CacheTrap achieves 100% targeted attack success on five open-source LLMs by using an efficient search to locate and flip a single bit in the KV cache as a transient trigger, while preserving normal accuracy without the trigger.

citing papers explorer

Showing 2 of 2 citing papers.

  • CacheTrap: Unveiling a Stealthier Gray-Box Trojan against LLMs cs.CR · 2025-11-27 · conditional · none · ref 9 · internal anchor

    CacheTrap achieves 100% targeted attack success on five open-source LLMs by using an efficient search to locate and flip a single bit in the KV cache as a transient trigger, while preserving normal accuracy without the trigger.

  • Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses cs.CR · 2026-03-28 · accept · none · ref 265 · internal anchor

    A multi-level taxonomy of risks, attacks, and defenses across the full embodied AI pipeline, synthesizing 500+ papers and flagging overlooked failure modes.