GradLock is introduced, a novel training-time injection attack that stealthily injects sensitive training data directly into the model parameters and employs dynamic gradient locking to prevent payload degradation during the optimization process.
Abstract
Existing model inversion (MI) attacks predominantly rely on post-training optimization to recover private data from model outputs. However, these methods are fundamentally constrained by the target model's generalization bottleneck, often yielding generic features rather than specific identities, particularly on high-dimensional datasets. In this paper, we introduce GradLock, a novel training-time injection attack that stealthily injects sensitive training data directly into the model parameters. Operating within a compromised supply chain context, GradLock leverages stateless deterministic indexing to establish isolated data vaults and employs dynamic gradient locking to prevent payload degradation during the optimization process. This mechanism allows the adversary to extract pixel-perfect data from the final model without retaining access to the training environment. Extensive experiments on MNIST, Imagenette, and CelebA demonstrate that GradLock achieves near-lossless reconstruction (SSIM ~ 1.0) and instant extraction (<1.0s). Compared to existing training-time injection methods, our approach exhibits superior robustness against standard deployment optimizations, including quantization, pruning, and fine-tuning. Furthermore, a user deployment study reveals that 93.3% of participants failed to detect the malicious logic, highlighting a severe blind spot in the security of modern AI supply chains.
Gecko is presented, designed to limit this additional risk while retaining a compact encrypted predictor, and formalizes ideal independence and information-preservation conditions as design guidance, then separately evaluate component-reuse extraction attacks.
Cheng'an Wei, Kai Chen, Yue Zhao et al.· 0 citations
A privacy-preserving zk-SNARK-based audit framework that searches for probes designed in the spirit of adversarial examples to amplify logit drift between an approved model and a modified deployment and demonstrates that token-based probes consistently deliver the strongest mean sensitivity across models and GPU platforms, although operating in a black-box setting.
Cameron Wilding, Mina Shaker, Fatemeh Ganji· 0 citations
Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint, demonstrates that a malicious parameter server can corrupt a PEFT adapter into a privacy backdoor: by assigning a dedicated memorization neuron to each training sample and ensuring each neuron updates at most once, the server can analytically reconstruct 59%--79% of client training data with high semantic fidelity. Existing defenses---including local differential privacy (LDP) and gradient clipping---either fail against this attack or impose unacceptable utility degradation. We present \textbf{TriShield}, a three-layer deterministic defense that completely prevents NeuroImprint-style reconstruction with zero model utility loss and no additional communication rounds. TriShield consists of: (1) a Parameter Artifact Detector that identifies memory-neuron signatures in distributed model parameters before local training begins; (2) a Stateful Virtual Iteration} mechanism that forces Adam/AdamW's momentum state to irreversibly entangle gradients across virtual steps, invalidating NeuroImprint's closed-form inversion; and (3) a Zero-Utility Orthogonal Projection operator that projects all local gradient updates onto the main-task semantic subspace computed via SVD, physically eliminating any gradient components that carry private memorization. We prove theoretically that after Layers 2 and 3, the mutual information between the uploaded gradient and any individual training sample is zero. Experiments on GPT-2 (117M) and Llama-Guard-3-1B verify that TriShield reduces NeuroImprint reconstruction rate to 0% across all tested attack variants, while maintaining or improving training accuracy, with less than 5% additional GPU computation overhead.
This paper presents a systematic framework for membership inference attacks, in which an adversary with only black-box query access to a deployed classifier determines whether a specific individual's record was part of its training set.
Pramod Prakash· International Journal of Int...· 0 citations
An improved defense mechanism that combines adversarial training and differential-privacy-style noise injection to collectively enhance the robustness of the existing KDk defense mechanism with marginal model utility trade-off is introduced.
N. Azeez, Oluwatobi Sunday Malomo, Omotolani Mary Okerinde et al.· Informatics· 0 citations
Anti Adversarial Training (AT-AT), a training regime that intentionally learns non-robust features to obtain both superior reconstruction defense and higher accuracy than state-of-the-art defenses, is introduced.
Rasmus Torp, Shailen K. Smith, Adam Breuer· 0 citations