pith. sign in

The dark deep side of DeepSeek: Fine-tuning attacks against the safety alignment of CoT-enabled models,

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 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

clear filters

representative citing papers

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs

cs.LG · 2026-05-01 · unverdicted · novelty 7.0

RouteHijack is a routing-aware jailbreak that identifies safety-critical experts via activation contrast and optimizes suffixes to suppress them, reaching 69.3% average attack success rate on seven MoE LLMs with strong transfer to variants and VLMs.

citing papers explorer

Showing 2 of 2 citing papers after filters.

  • RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs cs.LG · 2026-05-01 · unverdicted · none · ref 75

    RouteHijack is a routing-aware jailbreak that identifies safety-critical experts via activation contrast and optimizes suffixes to suppress them, reaching 69.3% average attack success rate on seven MoE LLMs with strong transfer to variants and VLMs.

  • AI-Generated PowerShell Malware: An Experimental Framework and Dataset cs.CR · 2026-06-29 · unverdicted · none · ref 76

    An experimental framework and annotated dataset show LLM-generated PowerShell malware triggers OS events with median 84.5% Jaccard overlap to real malware and 48.4% complete matches.