Vision-language models (VLMs) have recently shown remarkable capabilities in visual understanding and generation, but remain vulnerable to adversarial manipulations of visual content. Prior object-hiding attacks primarily rely on suppressing or blocking region-specific representations, often creating semantic gaps that inadvertently induce hallucination, where models invent plausible but incorrect objects. In this work, we demonstrate that hallucination arises not from object absence per se, but from semantic discontinuity introduced by such suppression-based attacks. We propose a new class of \emph{background-consistent object concealment} attacks, which hide target objects by re-encoding their visual representations to be statistically and semantically consistent with surrounding background regions. Crucially, our approach preserves token structure and attention flow, avoiding representational voids that trigger hallucination. We present a pixel-level optimization framework that enforces background-consistent re-encoding across multiple transformer layers while preserving global scene semantics. Extensive experiments on state-of-the-art vision-language models show that our method effectively conceals target objects while preserving up to $86\%$ of non-target objects and reducing grounded hallucination by up to $3\times$ compared to attention-suppression-based attacks.

Deep neural networks remain highly vulnerable to adversarial examples, and most defenses collapse once gradients can be reliably estimated. We identify \emph{gradient consensus} -- the tendency of randomized transformations to yield aligned gradients -- as a key driver of adversarial transferability. Attackers exploit this consensus to construct perturbations that remain effective across transformations. We introduce \textbf{DRIFT} (Divergent Response in Filtered Transformations), a stochastic ensemble of lightweight, learnable filters trained to actively disrupt gradient consensus. Unlike prior randomized defenses that rely on gradient masking, DRIFT enforces \emph{gradient dissonance} by maximizing divergence in Jacobian- and logit-space responses while preserving natural predictions. Our contributions are threefold: (i) we formalize gradient consensus and provide a theoretical analysis linking consensus to transferability; (ii) we propose a consensus-divergence training strategy combining prediction consistency, Jacobian separation, logit-space separation, and adversarial robustness; and (iii) we show that DRIFT achieves substantial robustness gains on ImageNet across CNNs and Vision Transformers, outperforming state-of-the-art preprocessing, adversarial training, and diffusion-based defenses under adaptive white-box, transfer-based, and gradient-free attacks. DRIFT delivers these improvements with negligible runtime and memory cost, establishing gradient divergence as a practical and generalizable principle for adversarial defense.

Quantum Federated Learning (QFL) merges privacy-preserving federation with quantum computing gains, yet its resilience to adversarial noise is unknown. We first show that QFL is as fragile as centralized quantum learning. We propose Robust Quantum Federated Learning (RobQFL), embedding adversarial training directly into the federated loop. RobQFL exposes tunable axes: client coverage $γ$ (0-100\%), perturbation scheduling (fixed-$\varepsilon$ vs $\varepsilon$-mixes), and optimization (fine-tune vs scratch), and distils the resulting $γ\times \varepsilon$ surface into two metrics: Accuracy-Robustness Area and Robustness Volume. On 15-client simulations with MNIST and Fashion-MNIST, IID and Non-IID conditions, training only 20-50\% clients adversarially boosts $\varepsilon \leq 0.1$ accuracy $\sim$15 pp at $< 2$ pp clean-accuracy cost; fine-tuning adds 3-5 pp. With $\geq$75\% coverage, a moderate $\varepsilon$-mix is optimal, while high-$\varepsilon$ schedules help only at 100\% coverage. Label-sorted non-IID splits halve robustness, underscoring data heterogeneity as a dominant risk.