Searcharxiv⌕ Search

arXiv subjects

Marjan Beheshti

Publications and source records attributed to Marjan Beheshti.

3 recordsLinked to original sources

KVMARK: Fragile Watermarking for KV-Cache Integrity in Latent Multi-Agent Systems

Latent multi-agent communication directly transfers Key-Value (KV) cache tensors between transformer-based agents, bypassing text serialization entirely. While computationally efficient and reasoning accurate, this communication channel is opaque and vulnerable to man-in-the-middle tampering, a threat vector unaddressed by existing text-based or behavioral watermarks, which cannot operate on continuous internal representations. To address this vulnerability, we propose KVMark, a training-free, zero-bit KV-cache watermarking framework to verify inter-agent handoff integrity. Our framework introduces four core technical components: (1) position-dependent sign patterns that guarantee first-order statistical invisibility while preserving downstream attention survival; (2) per-head sign patterns with aligned detection to defeat head-averaging attacks; (3) a three-tier depth-aware strength schedule that equalizes detection sensitivity across transformer layers while maintaining invisibility against nine statistical profiling strategies; and (4) content-bound key derivation that cryptographically binds watermarks to input contexts, preventing replay attacks under Kerckhoffs's principle. Empirical evaluation on a four-agent latent pipeline demonstrates $100\%$ detection across $1{,}500$ handoffs with a $0.0\%$ false positive rate ($\text{AUROC}=1.0$), $100\%$ layer-level tamper localization ($17/17$ attacked layers identified with $0/19$ false positives), and no statistically significant reasoning accuracy degradation across four benchmarks ($N{=}300$--$500$). Furthermore, the framework enables multi-hop cascade verification to isolate compromised agents (500/500 detection at three hops), withstands adaptive white-box adversaries and the Out-of-Sight DiffMean attack (up to $α=8.0$), and generalizes seamlessly to Qwen3-8B without re-tuning (1,500/1,500 TPR).

cs.CR↗

Attack-Resilient Multi-Bit Image Watermarking Framework via Latent Coordinate Sign Clamping

Watermarking is essential for image copyright protection and attribution, yet existing methods suffer from fundamental trade-offs among post-hoc applicability to pre-existing images, multi-bit capacity, training-free deployment, and adversarial resilience. To address these limitations, we propose a training-free watermarking framework that exploits the overcompleteness of diffusion latent spaces to embed multi-bit payloads into arbitrary images while preserving high visual quality. Additionally, we develop a three-layer decoding pipeline that combines magnitude-weighted majority voting, BCH, and Chase decoding to maximize message-extraction accuracy in the presence of channel noise. To counter active adversaries, our framework integrates a steganalysis-resistant noise camouflage layer and a dual-layer forgery defense that combines perceptual hashing with a Reed-Solomon fuzzy commitment scheme over CLIP features. Empirical evaluations demonstrate that our method applies to both natural and AI-generated images with a scalable $32\text{--}128$-bit capacity. Furthermore, it effectively mitigates advanced removal vectors ($94.6\%$ decode rate against CtrlRegen+ regeneration attacks) and secures robust forgery detection ($98.8\%$ accuracy via joint CLIP and RS fuzzy commitment mechanism).

cs.CR↗

Probing-Guided Layer Selection from Self-Supervised Speech Models for Generalizable Audio Deepfake Detection

Audio deepfake detection systems often fail to generalize across domains because they rely on features tied to specific attacks or recording conditions. Self-supervised speech models offer rich multi-layer representations, yet existing approaches either use a single layer or fuse all layers indiscriminately, and only reveal layer importance after training. We propose a model-agnostic, two-stage methodology that identifies informative depth zones before any task-specific model is trained. In the first stage, lightweight XGBoost probes evaluate each transformer layer's cross-domain discriminative power, producing a layer ranking. In the second stage, a compact neural classifier fuses only the selected layers through per-layer attention pooling and a shared bottleneck projection, while the backbone remains frozen. Applied across three backbones, the probing reveals two key findings. First, informative layers cluster in depth zones rather than at uniquely optimal positions: within-zone substitutions fall within multi-seed noise, while zone violations degrade performance by up to 5x. Second, the probing produces backbone-specific selections rather than a fixed layer recipe. On XLS-R-300M, four probing-selected layers with 1.34M trainable parameters achieve 4.94 +/- 0.32% equal error rate on In-The-Wild and 5.07% cross-domain average over four shared datasets, a 28% relative improvement over the best prior frozen-backbone result (Xiao and Vu, 2025) using all 25 layers with identical training data.

cs.SD↗