pith. sign in

Title resolution pending

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

2 Pith papers citing it

fields

cs.CL 1 cs.CR 1

years

2026 1 2023 1

verdicts

UNVERDICTED 2

representative citing papers

Detecting Language Model Attacks with Perplexity

cs.CL · 2023-08-27 · unverdicted · novelty 5.0

Jailbreak prompts with adversarial suffixes have high GPT-2 perplexity, and a LightGBM model on perplexity and length detects most attacks.

citing papers explorer

Showing 2 of 2 citing papers.

  • Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing cs.CR · 2026-05-11 · unverdicted · none · ref 73

    DR-Smoothing introduces a disrupt-then-rectify prompt processing scheme into smoothing defenses, delivering tight theoretical bounds on success probability against both token- and prompt-level jailbreaks.

  • Detecting Language Model Attacks with Perplexity cs.CL · 2023-08-27 · unverdicted · none · ref 48

    Jailbreak prompts with adversarial suffixes have high GPT-2 perplexity, and a LightGBM model on perplexity and length detects most attacks.