2026· Annual Meeting of the Association for Computational Linguistics· pp. 27014-27028· 0 citations· 39 references
Computer Science
TL;DR
RShield is proposed, a multi-bit backdoor watermarking that enables reliable user-level attri-bution of LLMs for EaaS under model extraction attacks, and achieves 100% multi-bit watermark recovery and high semantic fidelity under model extraction attacks compared to existing methods.
Abstract
Embedding-as-a-Service (EaaS) has emerged as a critical paradigm for commercializing large language models (LLMs). However, existing backdoor watermarking techniques are fundamentally limited to "zero-bit" detection, which prevents user-level traceability in multi-user EaaS scenarios. To address these limitations, we propose RShield, a multi-bit backdoor watermarking that enables reliable user-level attri-bution of LLMs for EaaS under model extraction attacks. RShield integrates Reed-Solomon error-correcting codes with orthogonal feature mapping to introduce highly-structured redundancy, constructing fault-tolerant symbol sequences for multi-bit watermark space, thereby staying recoverable even after aggressive extraction noise condition. To mitigate semantic distortion under the interference of noise channel, RShield employs a lightweight Adapter to adaptively inject multi-bit watermarks in the feature space, preserving the quality of EaaS while achieving a user-level traceability. Extensive experiments on four NLP benchmarks demonstrate that RShield efficiently achieves 100% multi-bit watermark recovery and high semantic fidelity under model extraction attacks compared to existing methods, while significantly reducing the degradation of watermarking on downstream task performance.
With the growing prevalence of large language model (LLM) generated content, watermarking is considered a promising approach for attributing text to LLMs and distinguishing it from human-written content. A prominent class of techniques embeds subtle but detectable signals in generated text by modifying token sampling probabilities. However, such methods are unsuitable for open-source models, where users have white-box access and can easily disable watermarking during inference. In this work, we introduce OpenStamp, a watermarking technique that encodes the watermarking logic directly into the model weights by modifying only the final projection, or unembedding, layer. Through experiments across two models, we show that OpenStamp achieves superior detection performance, with minimal degradation in model capabilities compared to prior methods. The implanted watermark is explicitly designed, and empirically confirmed, to be more robust to paraphrasing attacks and harder to scrub off through post-hoc fine-tuning than prior open-source watermarks. To enable developers to watermark their models, we release our code alongside watermarked versions of 4 popular open-source models.
While Large Language Models (LLMs) have gained remarkable success, they are consistently at risk of being stolen when deployed on untrusted edge devices. As a solution, TEE-based secure inference has been proposed to protect valuable model property. However, we identify a statistical vulnerability in existing protection methods, and furtherly compromise their security guarantees by proposed Model Stealing Attack with Prior. To eliminate this vulnerability, LoRO is presented in this paper, which leverages dense mask to completely obfuscate parameters. LoRO includes two innovations: (1) Low Rank Mask, which uses low-rank factors to generate dense masks efficiently. The computing complexity in TEE is hence reduced by an exponential amount to achieve inference speed up, while providing robust model confidentiality. (2) Factors Multiplexing, which reuses several cornerstone factors to generate masks for all layers. Compared to one-mask-per-layer, the secure memory requirement is reduced from GB-level to tens of MB, hence avoiding the hundred-fold latency introduced by secure memory paging. Experimental results indicate that LoRO achieve a 0 . 94 × Model Stealing (MS) accuracy, while SOTA methods presents 3 . 37 × at least. The averaged inference latency of LoRO is only 1 . 49 × , compared to the 112 × of TEE-shielded inference. Moreover, LoRO results no accuracy loss, and requires no re-training and structure modification. LoRO can solve the concerns regarding model thefts on edge devices in an efficient and secure manner, facilitating the wide edge application of LLMs.
Gaojian Xiong, Yu Sun, Jianhua Liu et al.· Advances in Neural Informati...· 5 citations
Foundation-model embeddings are now a primary data asset, but the content-provenance machinery built for images and audio does not transfer to them. C2PA binds to an asset with a stable bit-level or perceptual identity; embeddings have neither, since quantisation, projection, fine-tuning, and windowed averaging reshape them in normal use and break any fixed hash. We present HaloMark, a watermark for embedding vectors cryptographically bound to a C2PA manifest. It composes four standard primitives -- a block-diagonal orthogonal rotation, public whitening, an input-dependent LSH commitment, and a per-vector nonce -- around one protocol change: the producer signs the LSH commitment c into the C2PA sidecar, and the verifier reads c from the manifest instead of recomputing it. Recomputing is fragile under whitening, which flips the commitment bucket on 62% of inputs at cos = 0.96; reading the signed c reduces the verifier's score to T = T_null + beta(A)*epsilon, so security turns on a single scalar beta, which we bound rigorously for linear and non-adaptive attackers and characterise empirically for the adaptive case. We evaluate against an adversary holding polynomially many clean/watermarked pairs under one key with full sidecar visibility, across eight baselines and ten adaptive attackers including denoising-autoencoder removal. The eleven encoders separate at an empirical threshold eff_rank(Sigma)/d ~= 0.19: above it, detection AUROC stays at 0.98 or higher across every in-budget attack on the three encoders we sweep in full, and at 0.965 or higher under single-seed DAE removal on the rest; below it every variant we tested fails. Why the threshold is dimension-uniform is left open. Deployed as a Qdrant admission filter, the verifier runs at 284 us and 24 bytes of sidecar per vector, validated end-to-end against three C2PA reference-SDK bindings.
Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need. Generation-time schemes require access to the producing model and cannot be applied to third-party code, while post-hoc schemes work on any code but carry at most 4 bits of payload, far too few to distinguish the many deployed model configurations. We present multi-channel spread-spectrum watermarking, the first post-hoc, training-free code watermark with a 24-bit payload and formal robustness guarantees. The scheme encodes bits in variable naming conventions and in eight pairs of semantically equivalent code patterns, and a keyed pseudo-random permutation maps every site to a codeword bit so that each bit receives multiple independent votes. Majority voting absorbs distributed corruption, while an outer Reed-Solomon code recovers the identifier when concentrated channel attacks defeat the vote, yielding provable robustness bounds for formatting, syntactic, and structural attacks. Across 1,750 Python files from CodeNet and from GPT-4.1 and Llama-4 generations, the watermark achieves 100% clean-detection accuracy with zero false positives. Under 17 attack types, it recovers the identifier at 97.6% accuracy under 8 variable renames and 94.1% under 10% random per-site corruption, while the strongest post-hoc baseline collapses to 0% under any single-transform attack. Embedding and detection together take under 200 ms on CPU without training data or GPU.
These findings expose time as a first class security primitive in FL systems and recommend integrating timing randomization, lightweight monitoring, and scheduler level defenses into frameworks such as Tensor Flow Federated.
Barakat Saad Ibrahim, Ahmed Hameed Shakir, Hasan Jameel· Al-Noor Journal of Engineeri...· 0 citations
Although semantic watermarking is considered a promising safeguard for images generated by Latent Diffusion Models (LDMs), the reliance of the watermark detection pipeline on neural networks introduces a critical yet underexplored backdoor attack surface. To systematically study this vulnerability, we propose GhostVAE to plant a stealthy backdoor into the encoder of Variational Autoencoder (VAE), enabling reliable evasion of watermark detection. GhostVAE operates in two stages: it first constructs a universal trigger via power spectrum regularization to improve the trigger robustness, and then trains a backdoored VAE encoder with a parameter-aligned objective. Through extensive evaluations across three state-of-the-art semantic watermarking schemes and three widely adopted LDMs, we show that GhostVAE preserves watermark detection performance on benign images (achieving an average true positive rate of 94.4%), while simultaneously enabling highly effective evasion under trigger activation (achieving an average attack success rate of 94.6%). Moreover, we comprehensively analyze seventeen representative defenses and demonstrate that GhostVAE remains stealthy across the input space, parameter space, and latent space. Our work fundamentally undermines the trustworthiness of semantic watermarking systems and highlights that secure deployment of semantic watermarks requires end-to-end security considerations, particularly for neural network components.
Jinyuan Liu, Tianshuo Cong, Pei Li et al.· 0 citations