Haoliang Han

Yinpeng Dong, Peng Chen, Senyou Deng et al.

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track.

Xuchong Zhang, Changfeng Sun, Haoliang Han et al.

Recent studies have demonstrated that object detection networks are usually vulnerable to adversarial examples. Generally, adversarial attacks for object detection can be categorized into targeted and untargeted attacks. Compared with untargeted attacks, targeted attacks present greater challenges and all existing targeted attack methods launch the attack by misleading detectors to mislabel the detected object as a specific wrong label. However, since these methods must depend on the presence of the detected objects within the victim image, they suffer from limitations in attack scenarios and attack success rates. In this paper, we propose a targeted feature space attack method that can mislead detectors to `fabricate' extra designated objects regardless of whether the victim image contains objects or not. Specifically, we introduce a guided image to extract coarse-grained features of the target objects and design an innovative dual attention mechanism to filter out the critical features of the target objects efficiently. The attack performance of the proposed method is evaluated on MS COCO and BDD100K datasets with FasterRCNN and YOLOv5. Evaluation results indicate that the proposed targeted feature space attack method shows significant improvements in terms of image-specific, universality, and generalization attack performance, compared with the previous targeted attack for object detection.

Haoliang Han

Long-running language agents need mechanisms for deciding which experiences should persist after the working context is gone. Retrieval systems can reinsert past text, but they do not by themselves show that an experience has been selectively consolidated into the model's own behavior. We introduce EVAF, an Echo-Valence Attractor Field mechanism for gated LoRA consolidation, and a test-retest protocol for measuring selective parametric consolidation under controlled interference. Across GPT-2 and TinyLlama, EVAF preferentially consolidates high-valence, high-surprise experiences while preserving retrieval-accessible factual memory through a complementary routed memory path. Test-retest measurements show stronger post-interference behavioral persistence than frozen, retrieval-only, and ungated continual-update baselines, while keeping parameter drift and cross-persona contamination low. The results support a separation between memory access and memory depth: retrieving a fact and internalizing an experience are distinct computational operations.

Haoliang Han

How does an agent that can tell self from world come to be durably shaped by that distinction? Recent work shows that a predictive system can detect its own agency (Ye, 2026), but detecting agency does not explain durable, self-shaped behavior. We show that agency-gated slow credit -- a conjunctive term Own*Agency*Salience driving a slow parameter update -- produces post-unload behavioral residue: on a spiking substrate (Nengo LIF/PES), a learned self-preserving choice survives episodic buffer removal (retained fraction 0.96, N=50) and collapses when the slow decoders are reset or the agency gate is removed. Reproducing the agency comparator and toggling only the slow-credit channel, we find a clean dissociation: at matched agency gain, durable behavior develops only when self-credit performs slow work (post-unload self-preservation 1.00 vs 0.00). The same dissociation holds in 24-dimensional partially-observed control (0.74 vs 0.00), and a plastic-work analysis shows that basin deformation equals net self-credit work. Across eight sequentially-learned tasks under exogenous interference, the multiplicative veto also prevents forgetting: it retains old tasks (final post-unload accuracy 0.88, forgetting 0.13) where additive pooling collapses to chance-level recall, the no-agency ablation falls below chance, and episodic/replay baselines stay near chance after unload -- all with no replay buffer and no task-boundary-dependent protection mechanism (N=50). We formalize the durable residue as an operational behavioral self and argue that self-caused credit doing slow work is a necessary building block for agents that develop a self. No claim of consciousness is made.

Haoliang Han

Long-running language agents need more than memory access. Retrieval systems can fetch past facts at query time, but they do not decide which experiences should continue to shape behavior after the working context is unloaded. We study this separate problem as memory depth: durable goal-conditioned tendencies written into a small parametric store. We introduce the loop-drift protocol, a controlled stress test in which the retrieval index remains intact while working context is unloaded and goal-conditioned behavior must persist under long-loop interference. We evaluate EVAF, a surprise- and valence-gated LoRA consolidation mechanism. Across GPT-2 and TinyLlama, retrieval is strongest on shallow factual recall (short-fact accuracy 0.956--0.973), while EVAF is strongest on goal persistence and post-unload recovery (0.812--0.904) with only 2--3 parametric writes per 200 events. Mechanism controls show that selective consolidation factorizes into two controllable dimensions: selection and actuation. Matched random gates isolate selection beyond sparse writing; fixed-inner controls across GPT-2, TinyLlama, and Mistral-7B show that inner-loop write strength is model-dependent; and a Mistral-7B matched-gate inversion reveals asymmetric selection-actuation coupling under miscalibrated actuation. Public Memora event streams serve as an external diagnostic, exposing stale-memory invalidation as an unresolved boundary. Within this probe, selective parametric consolidation supplies memory depth distinct from and complementary to retrieval access.

Haoliang Han, Ziyuan Luo, Jun Qi et al.

Recent advances in editing technologies for 3D Gaussian Splatting (3DGS) have made it simple to manipulate 3D scenes. However, these technologies raise concerns about potential malicious manipulation of 3D content. To avoid such malicious applications, localizing tampered regions becomes crucial. In this paper, we propose GS-Checker, a novel method for locating tampered areas in 3DGS models. Our approach integrates a 3D tampering attribute into the 3D Gaussian parameters to indicate whether the Gaussian has been tampered. Additionally, we design a 3D contrastive mechanism by comparing the similarity of key attributes between 3D Gaussians to seek tampering cues at 3D level. Furthermore, we introduce a cyclic optimization strategy to refine the 3D tampering attribute, enabling more accurate tampering localization. Notably, our approach does not require expensive 3D labels for supervision. Extensive experimental results demonstrate the effectiveness of our proposed method to locate the tampered 3DGS area.