EvoKnow: Continual Knowledge Evolution for AI-Generated Image Detection

Zhiheng Peng; Wenwei Jin; Yangshi Ge; Siyu Xia; Jiawei Li; Xu Tang

cs.CVOct 8, 2026

EvoKnow: Continual Knowledge Evolution for AI-Generated Image Detection

Authors: Zhiheng Peng, Wenwei Jin, Yangshi Ge, Siyu Xia, Jiawei Li, Xu Tang

Organizations: Xiaohongshu Inc. · Southeast University

Abstract

AI-generated image detectors are commonly trained on fixed generator domains and become difficult to maintain as new generative models emerge. Continual adaptation is challenging because replaying historical generated images is costly, whereas updating shared parameters with limited current-domain data can overwrite prior forensic knowledge. We propose EvoKnow, a replay-free framework that formulates continual AI-generated image detection as forensic knowledge evolution. EvoKnow preserves a shared forensic basis learned from base domains, incrementally adds isolated residual experts for complementary generator-relevant evidence, and retrieves expertise through an Analytical Incremental Router (AIR) updated in closed form from current-stage generated images and accumulated sufficient statistics. Experiments demonstrate effective cross-generator generalization, few-shot expansion, and long-horizon continual adaptation. With ten generated images per arriving generator, EvoKnow achieves 96.70% average accuracy on non-base GenImage generators and 94.48% accuracy on Chameleon without target-benchmark adaptation. Under a strict replay-free continual learning protocol, EvoKnow achieves state-of-the-art continual learning performance, attaining 96.32% mean stage-wise accuracy and 4.32% average forgetting.

Figures & tables

Figure 1: Continual AIGC detection with EvoKnow. Instead of repeatedly reshaping a unified forensic space, EvoKnow freezes transferable shared evidence and incrementally adds isolated residual expertise for newly arriving generators. Historical synthetic images are not replayed.

Figure 2: Overview of EvoKnow. A global view and $K$ local views first pass through a frozen shared forensic learner. AIR performs expert retrieval over the base expert and isolated incremental residual experts. Within each expert, LoRA adapts semantic evidence shared by both branches, GPB emphasizes structural evidence in the global branch, and LFB emphasizes frequency evidence in the local branch. Cross-attention aggregates local evidence, which is fused with the global score for real-versus-synthetic prediction. When a new generator arrives, only its new incremental residual expert is trained and AIR is updated in closed form; the shared forensic learner and previously learned experts remain frozen, and historical synthetic images are not replayed.

Dataset	Generator / Metric	Existing Detectors Base: ProGAN									EvoKnow Base: SD v1.4
Dataset	Generator / Metric	CNNSpot	UnivFD	NPR	FatFormer	C2P-CLIP	AIDE ∗	SAFE ∗	MiraGe ∗	OmniDFA	Base	Exp.	Transfer
GenImage	SD v1.4 (base)	96.3	55.6	55.1	53.6	77.5	77.2	99.9	98.8	97.47 †	99.70	98.18	–
	BigGAN	46.8	84.4	57.7	82.2	85.9	50.6	77.4	96.5	97.33 †	93.80	93.77	–
	Midjourney	52.8	55.1	53.4	52.1	56.6	58.2	95.7	83.2	97.58 †	93.10	96.06	–
	SD v1.5	95.9	55.7	55.0	53.8	76.9	77.4	99.8	98.5	97.75 †	99.70	98.53	–
	ADM	50.1	62.5	43.8	61.4	71.6	50.4	59.5	82.7	85.50 †	78.10	96.21	–

Table 1: Cross-generator and cross-benchmark detection accuracy (%). Gray rows denote base domains and orange rows denote summary metrics; base domains are excluded from averages. Ave. averages non-base generators, while GAN Ave. and Diffusion Ave. summarize the corresponding UniversalFakeDetect groups. Existing-detector results follow their reported ProGAN-based protocols, whereas EvoKnow is initialized from GenImage SD v1.4; this is therefore a reported-result comparison rather than a controlled same-source evaluation. Base denotes the zero-shot shared forensic learner and base expert, Exp. denotes generator-based GenImage expansion with ten images per arriving generator, and Transfer evaluates Exp. directly on external benchmarks without target adaptation. EvoKnow columns are shaded in blue. Best and second-best summary values are shown in bold and underlined ; † denotes OmniDFA models trained with UniversalFakeDetect data.

Method	Observed-domain average accuracy ( $\mathrm{AA}_{t}$ , %)														Continual summary
Method	ProGAN	Deepfake	BigGAN	StyleGAN2	DDPM	ADM	DALL-E	GLIDE	SD v1.4	Midjourney	VQDM	SD v2.1	SDXL v1.0	SD v3.0	$\overline{\mathrm{AA}}\uparrow$	$\mathrm{AF}\downarrow$
Seq	99.99	94.46	81.01	94.05	90.35	80.14	79.66	76.68	84.50	73.82	74.31	51.90	57.29	73.85	79.43	23.04
Joint	99.99	98.77	99.34	99.57	98.15	98.97	98.81	98.54	98.80	98.30	98.38	95.69	95.17	96.01	98.18	1.77
ER Chaudhry et al. (2019)	99.99	98.26	96.77	96.96	90.92	85.97	86.18	84.65	84.11	83.94	83.73	84.51	86.02	90.68	89.48	12.10
EWC Kirkpatrick et al. (2017)	99.99	92.57	91.63	93.73	89.44	82.87	79.85	70.47	82.35	80.11	77.10	67.97	69.39	78.11	82.54	21.52
OSLA Ritter et al. (2018)	99.99	98.37	90.25	94.98	87.69	76.65	85.05	75.53	83.32	77.86	85.92	69.61	73.33	79.08	84.12	23.77

Table 2: Continual detection on the 14-stage multi-source benchmark of Wang et al. Wang et al. (2026a) , covering GANs, deepfakes, and diffusion models. ProGAN is the base domain, and each subsequent generator provides ten generated images for adaptation. Baselines follow their reported continual-learning protocols; Joint explicitly uses accumulated historical data. In contrast, EvoKnow neither retains nor replays historical generated images or their instance-level features, and uses task-agnostic real-image supervision for binary detection. The first 14 columns report stage-wise observed-domain accuracy

\mathrm{AA}_{t}

using the complete AIR pipeline;

\overline{\mathrm{AA}}

averages

\mathrm{AA}_{t}

over the trajectory, and AF is in percentage points. Baseline AF signs are converted for consistent comparison. Best non-Joint results are bolded, with ties highlighted once.

Figure 3: Expert retrieval and adaptation-sample analysis. (a) Generator-to-expert routing assignments. (b) Effect of the GenImage adaptation budget on cross-generator evaluation over UniversalFakeDetect, reported by average accuracy and across-generator standard deviation. UniversalFakeDetect is used only for evaluation.

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Phase	Hyperparameter	Value
Shared knowledge learning	Backbone	DINOv3-L/16
	Input resolution	$224\times 224$
	Global / local views	$1$ / $4$
	Optimizer	AdamW
	Learning rate	$5\times 10^{-6}$
	Weight decay	$10^{-2}$

Appendix

Table 4: Implementation details and hyperparameter settings.

Figure 4: Analytical illustration of the structural comparison in GPB. (a) A hard neighbor–center comparison and its sigmoid relaxations. (b) Derivatives with respect to the feature difference. The initial sharpness is

k=10

; the other values illustrate how sharpness changes the transition and gradient concentration. The hard comparison has zero derivative for

d\neq 0

and no ordinary derivative at

d=0

, indicated by an open marker.

Figure 5: Analytical illustration of spectral selection in LFB. (a) A hard high-pass mask at

c=0.25

and smooth masks with

\alpha=30

at three cutoff values. (b) Their derivatives with respect to the cutoff. The initial cutoff is

c=0.25

. The smooth mask provides cutoff gradients near the transition; the hard mask has zero cutoff derivative away from

\rho=c

. Frequency is measured on the patch-feature grid.

Stage	SD v1.4	BigGAN	VQDM	SD v1.5	Wukong	ADM	GLIDE	Midjourney	Seen	All
T1	99.69	93.78	95.67	99.69	99.74	78.05	95.52	93.10	99.69	94.41
T2	100.00	97.54	97.78	99.93	99.96	83.19	97.59	94.43	98.77	96.30
T3	100.00	97.54	97.77	99.93	99.96	83.19	97.59	94.42	98.44	96.30
T4	100.00	97.54	97.52	99.93	99.96	82.87	97.59	94.31	98.75	96.22
T5	100.00	97.32	97.42	99.93	99.96	81.54	97.03	94.08	98.93	95.91
T6	100.00	97.41	97.54	99.93	99.96	83.96	97.47	94.72	96.47	96.37

Appendix

Table 5: Complete generator-wise detection trajectory on GenImage. Generators arrive in the column order. Seen averages accuracy over the generators observed by the current stage; All averages accuracy over all eight generators, including those not yet observed. Bold marks the highest values in the Seen and All columns. All entries are percentages; averages are computed from the displayed generator-wise results.

Method

SD v1.4

BigGAN

VQDM

SD v1.5

Wukong

ADM

GLIDE

Midjourney

\uparrow

\downarrow

\uparrow

\downarrow

\uparrow

\downarrow

\uparrow

\downarrow

\uparrow

\downarrow

\uparrow

\downarrow

\uparrow

\downarrow

\uparrow

\downarrow

EvoKnow

99.69

–

98.77

-0.31

98.44

0.00

98.75

0.08

98.93

0.14

96.47

0.07

96.53

0.13

96.31

0.11

Appendix

Table 6: Stage-wise continual detection performance on GenImage. Each generator denotes its arrival stage. AA averages accuracy over the generators observed so far; AF measures the average signed performance drop relative to the accuracy obtained immediately after each generator is learned. AA is reported in percentages and AF in percentage points. AF is undefined at the first stage. Final-stage results are bolded.

Table 11

Method	Adaptation budget	GAN						Guided	LDM		GLIDE				DALL-E	Ave. $\pm$ Std.
		ProG.	Cycle	BigG.	Style	GauG.	StarG.		200	200-cfg	100	100/27	50/27	100/10
CNNSpot	CVPR’20	99.99	85.20	70.20	85.70	78.95	91.70	65.66	60.07	54.03	54.96	54.14	60.78	63.80	55.58	70.05 $\pm$ 14.90
PatchFor.	ECCV’20	75.03	68.97	68.47	79.16	64.23	63.94	68.52	67.41	76.50	76.10	75.77	74.81	73.28	67.91	71.44 $\pm$ 4.73
Co-occur.	EI’20	97.70	63.15	53.75	92.50	51.10	54.70	69.90	60.50	70.70	70.55	71.00	70.25	69.60	67.55	68.78 $\pm$ 12.69
Freq-spec	WIFS’19	49.90	99.90	50.50	49.90	50.30	99.70	50.40	50.90	50.40	50.40	50.30	51.70	51.40	50.00	57.55 $\pm$ 17.26
F3Net	ECCV’20	99.38	76.38	65.33	92.56	58.10	100.00	83.05	69.20	68.15	75.35	68.80	81.65	83.25	66.30	77.68 $\pm$ 12.48

Appendix

Table 9: UniversalFakeDetect detection accuracy (%) under zero-shot and few-shot knowledge expansion. Existing-detector results follow their reported ProGAN-based training protocols. For EvoKnow, the adaptation budget denotes the number of generated images per arriving generator in the GenImage stream; UniversalFakeDetect is used only for evaluation. The knowledge-unit organization and arrival sequence are fixed across adaptation budgets. The final column reports average accuracy and population standard deviation across the 14 displayed generators; the standard deviation measures cross-generator variation rather than variation across repeated runs.

Organization	MidJ.	SD1.4	SD1.5	ADM	GLIDE	Wuk.	VQDM	BigGAN	Ave.
Generator-based	96.06	98.18	98.53	96.21	96.27	98.64	97.41	93.77	96.88
Category-based	97.39	99.32	99.62	97.30	98.32	98.61	99.21	99.64	98.68
$\Delta$	+1.33	+1.14	+1.09	+1.09	+2.05	-0.03	+1.80	+5.87	+1.79

Appendix

Table 10: Effect of incremental residual knowledge organization on GenImage (%). Generator-based organization assigns one incremental residual expert per generator, whereas category-based organization groups generators into GAN, diffusion, and unknown-source categories. Both settings use ten generated images per arriving generator. Unlike Table 1 , Ave. here includes all eight GenImage domains, including the SD v1.4 base domain.

Method	Real	Big	Mid	Wuk	SD14	SD15	ADM	GLI	VQ	Avg.
ResNet	16.1	10.6	56.3	27.6	12.1	22.6	17.1	20.1	10.1	21.4
DIRE	22.6	11.6	0.0	26.6	22.1	20.6	18.1	22.6	10.6	17.2
ESSP	17.6	13.6	49.7	27.1	19.6	17.6	16.6	27.1	13.1	22.4
LIDA	83.4	98.5	69.3	13.1	23.6	50.3	47.2	55.3	45.7	54.0
EvoKnow (router)	98.5	93.1	29.5	35.7	2.1	65.0	63.5	68.0	38.1	54.8

Appendix

Table 11: Auxiliary source-attribution diagnostic (rank-1 accuracy, %). The evaluation includes one real-image class and eight generator classes. The real label is determined by the binary detection head, whereas generator labels are supplied by the analytical router. Avg. is the unweighted mean over all nine classes. Big, Mid, Wuk, GLI, and VQ abbreviate BigGAN, Midjourney, Wukong, GLIDE, and VQDM, respectively.

Explore similar work

DECODE: Tackling Representation and Decision Degradation in Continual AI-Generated Image Detection
Jul 30, 2026Zihao Cai, Xinghan Li, Ruiyan Yang +3Continual Learning AI-Generated Image Detection
Visual Laboratory of Fudan University, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China · CEC GienTech Technology Co., Ltd., Shanghai, China
Automated In-the-Wild Data Collection for Continual AI Generated Image Detection
May 4, 2026Thanasis Pantsios, Dimitrios Karageorgiou, Christos Koutlis +3AI-Generated Image Detection
Information Technology Institute, CERTH, Thessaloniki, Greece
RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection
Sep 29, 2026Wenpeng Mu, Junshan Jin, Tanfeng Sun +2Digital Image Forensics AI-Generated Image Detection
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China

Jul 30, 2026, cs.CVJ/K move · Enter open · S save

DECODE: Tackling Representation and Decision Degradation in Continual AI-Generated Image Detection

Zihao Cai, Xinghan Li, Ruiyan Yang, Xue Song+2

Visual Laboratory of Fudan University, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China · CEC GienTech Technology Co., Ltd., Shanghai, China

Continual Learning AI-Generated Image Detection Catastrophic Forgetting

Open paper AskPDF arXiv

As generative models continue to evolve, AI-generated image detectors must incrementally adapt to emerging generative domains while preserving knowledge acquired from previous ones. This continual learning setting is particularly challenging because forensic traces are often subtle and generator-specific, making detectors highly vulnerable to catastrophic forgetting. Existing methods primarily address this problem by stabilizing feature representations, implicitly treating forgetting as a representation-level issue. In this paper, we show that this perspective is incomplete. We demonstrate that even when feature representations remain discriminative, the decision boundary can progressively drift as the classification head is continually optimized on new domains. These two effects jointly give rise to a compound failure mode, termed Dual Degradation. To overcome this challenge, we propose DECODE, a decoupled continual detection framework that jointly mitigates representation- and decision-level forgetting. Specifically, we introduce Subspace Diversity Regularization (SDR) to preserve diverse forensic representations and Closed-Form Decision Alignment (CDA) to recalibrate the shared classification head after each adapter merge without manual hyperparameter tuning. Extensive experiments on 19 generative domains show that DECODE achieves an average accuracy of 99.36% with only 0.39% forgetting, while further generalizing to 11 unseen generators with 95.36% accuracy.

Abstract

Explore similar work

DECODE: Tackling Representation and Decision Degradation in Continual AI-Generated Image Detection

Automated In-the-Wild Data Collection for Continual AI Generated Image Detection

RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection