pith. sign in

Proceedings of the 37th International Conference on Machine Learning,

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

2 Pith papers citing it

fields

cs.CR 1 cs.CV 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

SDM: A Powerful Tool for Evaluating Model Robustness

cs.CV · 2026-05-19 · unverdicted · novelty 7.0

SDM is a new staged gradient attack that reconstructs the adversarial objective around probability differences and reports stronger performance than prior methods like APGD.

Adaptive Probe-based Steering for Robust LLM Jailbreaking

cs.CR · 2026-05-19 · unverdicted · novelty 5.0

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

Showing 2 of 2 citing papers.

  • SDM: A Powerful Tool for Evaluating Model Robustness cs.CV · 2026-05-19 · unverdicted · none · ref 5

    SDM is a new staged gradient attack that reconstructs the adversarial objective around probability differences and reports stronger performance than prior methods like APGD.

  • Adaptive Probe-based Steering for Robust LLM Jailbreaking cs.CR · 2026-05-19 · unverdicted · none · ref 37

    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.