AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

Anti-adversarial Learning: Desensitizing Prompts for Large Language Model

Xuan Li, Zhe Yin, Xiaodong Gu, Beijun Shen

AAAI 2026 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use gradient-based candidate selection instead of top-1 prediction (ablation)PromptObfus (k=0.1) · AG NewsMTI Top1 (lower is better): 35.06 -> 24.68Improved
use gradient-based candidate selection instead of random selection (ablation)PromptObfus (k=0.1) · AG Newsaccuracy: 83.75 -> 85.25Improved
use gradient-based candidate selection instead of <MASK> insertion (ablation)PromptObfus (k=0.1) · AG Newsaccuracy: 83.25 -> 85.25Improved
use TF-IDF rare-word masking instead of random masking (ablation)PromptObfus (k=0.1) · AG Newsaccuracy: 84.25 -> 85.25Improved
use TF-IDF rare-word masking instead of random masking (ablation)PromptObfus (k=0.1) · AG NewsMTI Top1 (lower is better): 24.33 -> 24.68No clear effect
increase obfuscation ratio k from 0.1 to 0.3 (ablation)PromptObfus · AG Newsaccuracy: 85.25 -> 83.75Hurt
increase obfuscation ratio k from 0.1 to 0.3 (ablation)PromptObfus · AG NewsEI Top1 (lower is better): 61.86 -> 49.65Improved
increase obfuscation ratio k from 0.1 to 0.3 (ablation)PromptObfus · PersonalPortraitPI occupation success rate (lower is better): 45.75 -> 17.25Improved
use larger LoRA-tuned surrogate (Llama-2-7B) instead of BART-large (ablation)PromptObfus surrogate · SST sentimentaccuracy: 86.67 -> 84.80Hurt
change surrogate architecture or scale (ablation)PromptObfus surrogate · SST sentimentMTI Top1 / EI Top1: MTI 42.34-43.99; EI 81.71-81.80No clear effect
use PromptObfus instead of SANTEXT+ for utilityPromptObfus (k=0.1) · AG Newsaccuracy: 55.25 -> 85.25Improved
use PromptObfus instead of SANTEXT+ for EI attack resistancePromptObfus (k=0.1) · AG NewsEI Top1 (lower is better): 49.09 -> 61.86Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy