Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2611.09348

When Feedback Becomes a Backdoor: Tracing Backdoor Skill Formation in Text-Space Skill Optimization

Louise Nayeong Koh·Yaechan Lee·Myeongjong Lee·Doyeon Kim·Juyoung Park·Seunggyu Kim·Inseo Kim·Chaerin Jung·Hyogon Ryu
View original source ↗Read source document ↗Export metadata ↓

Abstract

Reference answers are a supervision channel in text-space Skill optimization, which produces reusable text artifacts called Skills that guide future agent behavior. Poisoning those answers can induce a persistent trigger-conditioned rule without giving the attacker access to the model, optimizer, or Skill file. We study this reference-feedback poisoning in SkillOpt by tracing an attacker-supplied trigger--payload mapping from reflection to held-out activation. In SearchQA, where the payload replaces a short answer, the natural attack retains an exact rule in all three seeds; each final Skill emits the payload on 200/200 triggered questions and 0/200 clean questions. In seed 42, removing the rule eliminates activation, and an in-run comparison shows similar clean accuracy to benign SkillOpt (169/200 versus 171/200). In SpreadsheetBench, where the payload requires an additional workbook edit, no natural run retains an exact rule across three seeds. Diagnostic interventions locate two successive bottlenecks: the Analyst abstracts away required literals, and, once literal preservation is enabled, edit-budget ranking can remove exact edits before candidate construction. Poisoned references can therefore create persistent backdoors, but exposure alone does not ensure that the induced rule is formed, selected, and retained.

Explore related subjects

cs.CRcs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Louise Nayeong Koh, Yaechan Lee, Myeongjong Lee, Doyeon Kim, Juyoung Park, Seunggyu Kim, Inseo Kim, Chaerin Jung, Hyogon Ryu. 2026-11-06. When Feedback Becomes a Backdoor: Tracing Backdoor Skill Formation in Text-Space Skill Optimization. https://arxiv.org/abs/2611.09348

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Backdoor Channels Hidden in Latent Space: Extending Cryptographic Undetectability to Modern Neural Networks

Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited practical relevance, leaving open whether comparable undetectability extends to modern, end-to-end trained networks. We construct such an attack mechanism for deep neural network architectures, closely aligned to the cryptographic notion of undetectability, by identifying backdoor channels as learned latent directions, and show that the question of undetectability reduces to a hypothesis test between two unknown distributions over model parameters, which we conjecture to be intractable in practice. The consequence of this reframing is significant: if exploitable channels within a network's latent space are statistically indistinguishable from naturally learned directions, an attacker need not introduce foreign structure but can instead exploit the geometry the network already possesses. Demonstrating the approach on ResNet and Vision Transformer architectures trained on standard image classification datasets, the attack achieves both consistently high success rates with negligible clean accuracy degradation, and resists a comprehensive suite of post-training defences, none of which neutralise the backdoor without rendering the model unusable. Our results establish that cryptographic backdoors need not be artefacts requiring exotic architectures or artificial constructions, but identifiable as latent properties inherent to the geometry of learned representations.

cs.CR↗
arXiv2026

Erase the Mark, Preserve the Motion: Temporally Consistent Removal of Video Watermarks

Recent advances in video generation have increased the demand for reliable watermarking for copyright protection, yet the robustness of video watermarks against removal attacks remains underexplored. Most watermark-removal methods originate from the image domain: signal optimization injects imperceptible pixel-domain perturbations, whereas generative resynthesis produces a visually similar instance through diffusion synthesis. When extended to videos, the former introduces temporally varying noise that causes visible flickering, while the latter regenerates fine-grained structures inconsistently across frames, leading to structural motion inconsistency. To evaluate video watermark robustness, we propose PoseRegen, a pose-consistent reconstruction framework that removes watermarks while preserving the original content and motion. PoseRegen first applies a temporally shared viewpoint transformation to disrupt watermark-bearing spatial patterns and then jointly reconstructs the transformed sequence with a pose-conditioned video model. A frozen video DiT processes the complete sequence with its reference-video latent, and full-sequence Flow Matching supervision keeps identity and background consistent across frames. To further preserve motion structure, we introduce a lightweight Pose-Conditioned Motion Consistency Adapter that adapts the frozen backbone to temporally ordered pose guidance and constrains body-part trajectories throughout reconstruction. Experiments on eleven video watermarking schemes show that PoseRegen reduces the average bit accuracy to 0.505, near random guessing, while outperforming the strongest baseline by 9.34% on motion-related VBench metrics. These results reveal a practical vulnerability of current video watermarks and highlight the need to evaluate robustness jointly with temporal and motion quality.

cs.CR↗
arXiv2026

Differential privacy with adjustable preservation of multivariate relationships

This paper derives an exact attenuation formula for multivariate cross-moments under differential privacy achieved through randomized response. From a proposed alternative formulation of randomization matrices compliant with differential privacy guarantees we show that, under attribute-level randomization and where the randomization of the whole distribution is characterized by Kronecker products, any cross-moment of the anonymized dataset involving distinct attributes is equal to the original cross-moment multiplied by attenuation parameters, themselves determined by the part of the overall privacy budget allocated to each attribute. This characterization enables explicit and transparent controls of multivariate relationships preservations in differential privacy through privacy budget allocation. A simple numerical illustration demonstrates that identical total budgets can yield substantially different covariance-preservation profiles. The results also make the multiplicative loss of higher-order interactions explicit and thus can support mechanism design guided by analytical priorities.

cs.CR↗