Searcharxiv⌕ Search

arXiv subjects

Seok-Hwan Choi

Publications and source records attributed to Seok-Hwan Choi.

3 recordsLinked to original sources

Where Is Rank-1 DiM Refusal Intervenable in Multimodal LM Derivatives?

Open-weight model hubs now ship not only chat checkpoints but a long tail of derivatives---fine-tunes, safety guards, vision--language models (VLMs), audio wrappers, and generative heads---yet residual-stream safety audits still often intervene at a single site, usually the text decoder $T$. We ask a localization question under one shared mean / rank-1 difference-in-means (DiM) extract$=$intervene protocol, with matched-norm random and empty-rate controls: does causal chat attack lift concentrate at $T$, or do perceptual encoders, projectors, and fusion paths ($E$/$P$/$F$) supply a comparable bypass? On the mixed-input settings we stress-test---HADES adversarial images paired with harmful text prompts, and spoken AdvBench via text-to-speech (TTS) or silence---text DiM at $T$ raises attack success rate (ASR) while the same mean DiM at $E$/$P$/$F$ does not; attacks track harmful text rather than image or audio content. Margin-rank and leverage probes on a Vision leaf show that this recipe is extremal at $T$ and near chance at $P$/$E$, which pressures a weak-extractor reading of those flat cells for the DiM family we study. Catalog breadth and mapper-free base$\to$derivative transfer when residual widths match provide supporting coverage under the same gates; generative U-Nets are a separate band under generation judges. The primary claim is this recipe-scoped $T$ vs.\ non-text intervenability asymmetry---intervention accessibility under mean / rank-1 DiM, not a claim that refusal is absent or fully represented outside $T$ (text vs.\ perceptual contrasts and pooling differ by site). On VLGuard Unsafe prompts ($n{=}200$; Llama-Guard), the same $T$ vs.\ $P$/$E$ directionality holds at modest absolute ASR ($0.030{\to}0.150$ at $T$). An intervention-oriented Class$\times$site ledger records where this protocol still hooks as supporting coverage, not as a universal multimodal bypass.

cs.LG↗

Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components

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.

cs.CR↗

DPAC: Distribution-Preserving Adversarial Control for Diffusion Sampling

Adversarially guided diffusion sampling often achieves the target class, but sample quality degrades as deviations between the adversarially controlled and nominal trajectories accumulate. We formalize this degradation as a path-space Kullback-Leibler divergence(path-KL) between controlled and nominal (uncontrolled) diffusion processes, thereby showing via Girsanov's theorem that it exactly equals the control energy. Building on this stochastic optimal control (SOC) view, we theoretically establish that minimizing this path-KL simultaneously tightens upper bounds on both the 2-Wasserstein distance and Fréchet Inception Distance (FID), revealing a principled connection between adversarial control energy and perceptual fidelity. From a variational perspective, we derive a first-order optimality condition for the control: among all directions that yield the same classification gain, the component tangent to iso-(log-)density surfaces (i.e., orthogonal to the score) minimizes path-KL, whereas the normal component directly increases distributional drift. This leads to DPAC (Distribution-Preserving Adversarial Control), a diffusion guidance rule that projects adversarial gradients onto the tangent space defined by the generative score geometry. We further show that in discrete solvers, the tangent projection cancels the O(Δt) leading error term in the Wasserstein distance, achieving an O(Δt^2) quality gap; moreover, it remains second-order robust to score or metric approximation. Empirical studies on ImageNet-100 validate the theoretical predictions, confirming that DPAC achieves lower FID and estimated path-KL at matched attack success rates.

cs.CV↗