SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.06771 · 2026

AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models

Bo Han, Qizhou Wang, Kemou Li, Fengpeng Li, Jiantao Zhou

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.06771.json · badge: /api/ran/2602.06771.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Feng-peng-Li/AEGIS community
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
GP Ran
ran on a synthesized input
Feng-peng-Li/AEGIS/train-scripts/AEGIS.py
pointer only (licence: CC-BY-4.0) · get_code("ea33a36bf5182425")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Feng-peng-Li/AEGIS, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

AEGIS Not yet run
unverified (harvested, no recorded run)
Feng-peng-Li/AEGIS/train-scripts/AEGIS.py
pointer only (licence: CC-BY-4.0) · get_code("74c1234d3d459a5a")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Feng-peng-Li/AEGIS, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

CustomTextEncoder Not yet run
unverified (harvested, no recorded run)
Feng-peng-Li/AEGIS/train-scripts/AEGIS.py
pointer only (licence: CC-BY-4.0) · get_code("7fb6556e89ee8a51")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Feng-peng-Li/AEGIS, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness-retention trade-off. Robustness means the model fine-tuned by concept erasure methods resists reactivation of erased concepts, even under semantically related prompts. Retention means unrelated concepts are preserved so the model's overall utility stays intact. Both are critical for concept erasure in practice, yet addressing them simultaneously is challenging, as existing works typically improve one factor while sacrificing the other. Prior work typically strengthens one while degrading the other-e.g., mapping a single erased prompt to a fixed safe target leaves class-level remnants exploitable by prompt attacks, whereas retention-oriented schemes underperform against adaptive adversaries. This paper introduces Adversarial Erasure with Gradient-Informed Synergy (AEGIS), a retention-data-free framework that advances both robustness and retention. First, AEGIS replaces handpicked targets with an Adversarial Erasure Target (AET) optimized to approximate the semantic center of the erased concept class. By aligning the model's prediction on the erased prompt to an AET-derived target in the shared text-image space, AEGIS increases predictednoise distances not just for the instance but for semantically related variants, substantially hardening the DMs against state-of-the-art adversarial prompt attacks. Second, AEGIS preserves utility without auxiliary data via Gradient Regularization Projection (GRP), a conflict-aware gradient rectification that selectively projects away the destructive component of the retention update only when it opposes the erasure direction. This directional, data-free projection mitigates interference between erasure and retention, avoiding dataset bias and accidental relearning. Extensive experiments show that AEGIS markedly reduces attack success rates across various concepts while maintaining or improving FID/CLIP versus advanced baselines, effectively pushing beyond the prevailing robustness-retention trade-off. The source code is in https://github.com/Feng-peng-Li/AEGIS.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.06771")
get_code_for_paper("2602.06771")
have("2602.06771")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.06771.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.06771.svg)](https://syntology.ai/paper/2602.06771)

Connect an agent — have() is free.