Gradient-Based Attacks

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 37

Sep 29, 2026cs.CR

LogiC-Diff: Embedding Security Properties Into AI-Enabled Cyber-Physical Systems

AI-enabled Cyber-Physical Systems (CPS) are highly vulnerable to adversarial and anomalous inputs, where small perturbations can induce cascading errors and unsafe control actions. Existing approaches, such as rule-based filtering, training-time regularization, or diffusion-based reconstruction, either operate outside the model or lack mechanisms to incorporate formal security specifications into the prediction process. In this paper, we take the first step toward embedding security properties directly into AI-enabled CPS, enabling predictive models to enforce system-level constraints during inference rather than relying on external defenses. We introduce a logic-conditioned bi-stage diffusion framework that integrates Signal Temporal Logic (STL) specifications into forecasting. STL serves as a first-class conditioning signal that guides both an input repair stage and an output refinement stage, allowing the model to jointly mitigate adversarial perturbations and enforce desired temporal behaviors to satisfy security-critical properties. We evaluate our approach on two real-world multivariate CPS forecasting datasets under a diverse set of physical sensor and cyber attacks. Across sensor faults, gradient-based attacks, adaptive attacks, and varying attack strengths, our method consistently improves robustness and specification compliance, degrades more gracefully as attack strength increases, and generalizes better to unseen attacks. Ablation studies on specification coverage and quality further show that embedding logical security properties yields gains unattainable by reconstruction-based methods alone, highlighting a new direction for integrating formal methods with generative models in secure CPS.

Ziyan An, John Stankovic, Meiyi Ma

Department of Computer Science Vanderbilt University Nashville, TN · Department of Computer Science University of Virginia Charlottesville, VA

Cyber-Physical System Cybersecurity Gradient-Based Attacks Security Diffusion Models

Sep 29, 2026cs.LG

A Sharp Transition in Data Reconstruction under Differential Privacy

Data reconstruction attacks have empirically been successful in recovering training samples from learned models, raising privacy concerns and motivating defenses with guarantees that remain valid against future threats. While differential privacy (DP) provides formal protection, choosing the privacy budget remains a challenge: small budgets severely reduce utility, but it is hard to quantify how large the budget can be without allowing accurate reconstruction. In this work, we study informed attackers who aim to reconstruct a single

d

-dimensional training sample from a

ρ

-zero-concentrated DP model, knowing all other training data. Our main contribution is to establish a sharp transition at

ρ\asymp d

for data reconstruction: on the one hand, we derive entropy-based lower bounds for any private mechanism and any attack, characterizing a set of target priors for which reconstruction is information-theoretically impossible for

ρ\ll d

; on the other hand, we analyze a simple attack on private linear regression with output perturbation, showing that reconstruction is practically feasible for

ρ\gg d

. Remarkably, the transition moves to

ρ\asymp s

for data lying in an

s

-dimensional subspace, demonstrating that the privacy budget guaranteeing adequate protection must be assessed in terms of the effective dimension of the data. We validate our findings via experiments on synthetic data and natural images (CIFAR-10, ImageNet).

Max Cairney-Leeming, Simone Bombari, Marco Mondelli

Institute of Science and Technology Austria

Gradient-Based Attacks Distributional Fidelity Sharp Transitions

Sep 28, 2026cs.CV

Stealth Is a Relation, Not a Property: How Event Representations Create Blind Spots for Timing Attacks in Event-Based Perception

An event camera produces an asynchronous stream, but what is visible in that stream depends on how a downstream consumer, such as a model or detector, processes time. The same timestamp change may leave a coarse temporal representation unchanged while changing the response of a model that preserves finer timing. We characterize this dependence as observer-relative stealth. For recorded event streams, retiming an event within its protected accumulation window leaves the accumulated integer tensor exactly unchanged. We use this exact blind space to construct Null, a gradient-guided timestamp-retiming attack, and define SC-ASR_A(tau) to measure attack success while bounding the change visible to observer A. On DVS Gesture at a 10% event budget, Null reaches 81.56 +/- 5.81% ASR on ConvSNN and 98.67 +/- 0.45% on a GRU while preserving the protected tensor exactly. On DailyDVS-200, a protocol-scale Multi-View Fusion Network variant reaches 99.28 +/- 0.11% exact-null ASR, compared with 9.70 +/- 1.06% for its matched control. In a five-attack comparison, Null is the only method with nonzero attack success at exact observer equality, reaching 81.4% on DVS Gesture and 87.35% on DailyDVS-200. We also search the same exact blind space with an independently implemented constrained projected-gradient optimizer, C-PGD. At matched victim-gradient evaluations, C-PGD reaches 84.50 +/- 2.89% ASR on DVS Gesture and 89.55 +/- 4.39% on DailyDVS-200, again with exact protected equality. Perturbations that are exactly hidden from the protected observer become visible under shifted, finer, overlapping, and randomized temporal views. Adding observer constraints reduces the real-valued blind-space fraction from 87.5% to 75.0% to 62.5%, while DVS ConvSNN ASR falls from 74.9% to 61.9% to 37.2%. These results show that stealth is not a property of the perturbation alone.

Shoaib Ahmed Dipu, Md. Shaown Miah, Kamrul Hasan +1

Indiana University Indianapolis · Bangladesh University of Engineering and Technology · Tennessee State University

Attack Stealthiness Video Surveillance Gradient-Based Attacks Blind Spots Cross-View Fusion Automatic Speech Recognition

Sep 24, 2026cs.LG

Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning

Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy gradients to the server. Yet temporal structure can amplify this leakage beyond single-frame attacks. We introduce Temporal Reconstruction Attack on Consecutive Encodings (TRACE), an amortized temporal gradient-inversion attack that autoregressively reconstructs the sequence of private observation-action trajectories from per-step policy-learning gradients. The attack exploits two structural signals ignored by prior single-frame methods: (i) cross-time correlation between successive embodied gradients, which we formalize via a conditional mutual-information bound, and (ii) closed-form action recovery from policy-head gradient structure, which we prove exact when standard entropy regularization is sufficiently small. On held-out embodied scenes, TRACE reaches

18.8

dB PSNR with near-perfect action recovery at

3

-

4.5

ms per reconstructed frame, dominating the learning-based baseline across all reconstruction metrics and exceeding optimization attacks while running orders of magnitude faster. Further evaluation demonstrates TRACE's broader applicability across recurrent, residual, and compact transformer victim architectures, multi-modal inputs, and larger discrete action spaces. Defense experiments suggest that protecting temporal gradient streams may require sequence-aware privacy mechanisms.

Sudip Bhujel, Shanghao Shi, Ruiquan Huang +2

Department of Computer Science, University of Kentucky · Department of Computer Science and Engineering, Washington University in St. Louis

Gradient-Based Attacks Offline Reinforcement Learning Diffusion Inversion Gradient

Sep 11, 2026cs.CL

Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs

Per-layer differential privacy (DP) clipping improves gradient fidelity in federated learning by allocating per-matrix clipping budgets proportional to parameter count. We show that this recipe breaks for speech large language models (speech-LLMs), when the acoustic encoder and the language decoder differ by an order of magnitude in update norm. Single-pool per-layer methods suffer \emph{cross-component budget collapse}, dragging word error rate (WER) far from flat global clipping or collapsing training entirely. When the norm imbalance is milder, adaptive single-pool methods partially recover, confirming that collapse severity scales with the inter-component norm ratio. We empirically diagnose the root cause across six per-layer methods and three speech-LLM architectures. We then propose \emph{

\alpha

-split}, a two-pool allocation that normalises encoder and LLM parameters into independent pools, and show that joint

\ell_2

sensitivity and the original

(\varepsilon,\delta)

-DP guarantee are unchanged. At architecture-calibrated

\alpha

, our method recovers WER utility compared to flat DP, while granting the encoder

4.47{\times}

tighter per-component noise protection against speaker voice-based gradient-inversion attacks at only

+2.6\%

LLM noise overhead.

Jordi Luque, Fernando López, Aleix Sant

Scientific Research Telef´onica Innovaci´on Digital Barcelona, Spain · Telef´onica Innovaci´on Digital Universidad Aut´onoma de Madrid Madrid, Spain · Scientific Research Telef´onica Innovaci´on Digital Universitat Polit`ecnica de Catalunya Barcelona, Spain

Standard Differential-Privacy Gradient-Based Attacks Token Budget Allocation

Sep 10, 2026cs.LG

Cascading Gradient Inversion via LT-Code Inspired Peeling in Federated Learning

Federated learning shares model updates rather than raw data, yet these updates can be inverted to reconstruct the clients' training data. Analytic reconstruction attacks, which invert a gradient in closed form, degrade as the batch grows: prior single-round attacks recover only about half of a batch of size

100

even when the attacker fully controls the network parameters, and known upper bounds limit what any such method can recover. We establish a connection between gradient inversion and the theory of erasure-correcting codes, and use it to construct attacks that exceed these bounds. Our attacks recover batches exactly, together with every sample's label, from a single FedSGD round, and certify each recovery without ground-truth data. On eight image and tabular benchmarks they outperform prior single-round attacks by a wide margin. Even a passive attacker who only observes an honestly trained network recovers

94

--

100\%

of ImageNet batches at sizes up to

128

, more than prior single-round attacks achieve even with active manipulation of the model, and in the active setting more than

90\%

is recovered at batch sizes of several hundred. These results show that the privacy leakage of federated learning has been underestimated.

Saeed Shariati, Mohsen Alambardar Meybodi

Department of Applied Mathematics and Computer Science, Faculty of Mathematics and Statistics, University of Isfahan, Isfahan 81746-73441, Iran

Federated Learning Gradient-Based Attacks Diffusion Inversion Stochastic Gradient Descent Error Correction

Sep 8, 2026cs.CR

DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory

Diffusion watermarking embeds verifiable signals into the generative process and commonly verifies them by recovering trajectory-dependent evidence, making the marks robust to conventional pixel-space distortions. Existing removal attacks either regenerate along deterministic trajectories, which often preserve the watermark-bearing latent structure, or optimize every image separately. We identify the reliance on a recoverable generative trajectory as a common attack surface among the schemes we study. Based on this observation, we propose DRIFT, a black-box attack that combines partial forward diffusion with stochastic reverse resampling. Forward re-noising limits source information available to a fixed-depth recovery pipeline, while stochastic reversal supplies alternative noise-driven paths whose removal benefit we isolate through matched sampler comparisons. Adaptive DRIFT searches a selected ladder for each image's first verifier-rejected rung and refines fidelity while retaining only updates rejected by the same verifier. At fixed depth, we derive information-theoretic and Wasserstein source-dependence bounds; under realized-ladder monotonicity, the first rejected rung is least distorted among rejected rungs on that ladder, and verifier-gated refinement preserves rejection. Across nine watermarks spanning three paradigms, DRIFT achieves 98-100% attack success and the best image quality among the compared attacks, without secret keys, verifier internals, or per-image gradient optimization.

Rui Bao, Zheng Gao, Xiaoyu Li +3

University of New South Wales · Griffith University

Watermarks Gradient-Based Attacks Diffusion Models

Aug 30, 2026cs.CL

TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization

Gradient-based jailbreak suffix optimization methods typically update the suffix by retaining the candidate with the lowest current loss. We show that this seemingly natural design is fundamentally myopic: candidates that look better under the current-step proxy often fail to produce better jailbreak outcomes later in the search, revealing a form of selection-stage reward hacking. This suggests that candidate selection, rather than candidate generation alone, is a hidden bottleneck in suffix optimization. To address this issue, we propose TACS, a trajectory-aware candidate selection framework for jailbreak suffix optimization. Instead of selecting candidates solely by their immediate loss, TACS augments per-step evaluation with a trajectory-aware proxy and stabilizes selection with reference-policy regularization and a discriminator-estimated chi-squared correction, encouraging choices that remain effective beyond the current step. Experiments on HarmBench show that TACS consistently outperforms strong baselines under the same search budget, substantially improving attack success rates while exhibiting more stable optimization behavior throughout the search. Our findings highlight that mitigating selection-stage reward hacking caused by myopic candidate selection is critical for improving jailbreak suffix optimization.

Shiliang Xiao

Jailbreak Attacks Jailbreaks Large Language Model Jailbreaks Gradient-Based Attacks Surrogate Gradient Attack-Success Rate+2

Aug 12, 2026cs.LG

GENADA: efficient generative time series adversarial attack framework

Deep learning models are widely used for time series analysis in domains such as healthcare, finance, energy systems, and environmental monitoring. However, these models remain vulnerable to adversarial attacks, where small input perturbations cause severe degradation in predictive performance. Commonly used gradient-based attacks, iterative first-order methods, are computationally burdensome, as they repeatedly backpropagate through the victim model to compute input gradients during a number of iterative refinement steps. We propose a GENerative ADversarial Attack (GENADA) that learns a generative model to produce deceptive perturbations directly in a single forward pass and a procedure to train it. Variants include single-step and iterative generative attack schemes. The validation considers attacks on several neural models and datasets in the time-series domain, a controlled, low-dimensional setting. Empirically, GENADA achieves comparable attack quality to strong baselines while requiring less time to generate perturbations during inference.

Michael Baronov, Denis Vorobev, Margarita Rusanova +2

Moscow Independent Research Institute of Artificial Intelligence · HSE University

Black-Box Adversarial Attacks Gradient-Based Attacks Time-Series Generation Time Series Deep Learning

Aug 2, 2026cs.AI

MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning

Parameter-efficient fine-tuning (PEFT), such as low-rank adaptation (LoRA), has recently been adopted in federated learning to reduce communication and computation costs. In this setup, users download a pretrained model from the server prior to fine-tuning, and then fine-tune lightweight LoRA modules locally while keeping the pretrained model frozen, sharing only the gradients of the fine-tuning parameters with the server. Despite its growing popularity, robustness of federated fine-tuning against an adversarial server remains underexplored, where the server maliciously tampers with the training protocol to breach the privacy of users' data. In this work, we investigate gradient inversion attacks on LoRA fine-tuning. We propose an analytical attack that enables a malicious server to recover private user data by leveraging a poisoned pretrained model and fine-tuning parameters. Our design embeds fine-tuning data within the shared gradients, to allow the server to analytically reconstruct user data. Unlike prior works, our attack is applicable to both language and vision tasks, does not rely on computationally expensive (adversarial) pretraining with public datasets or require the number of training tokens to be less than the rank of LoRA modules. Experimental results on both language and vision tasks demonstrate high-fidelity data recovery across multiple baselines, revealing several critical vulnerabilities.

Hasin Us Sami, Swapneel Sen, Basak Guler

University of California, Riverside, CA

Gradient-Based Attacks Federated Learning Adversarial Robustness

Jul 13, 2026quant-ph

When cheap gradients fail: the measurement cost of attacking quantum classifiers

Adversarial perturbations threaten machine learning classifiers, including variational quantum classifiers. We show that finite quantum measurement statistics (shot noise) act as a built-in defense against gradient-based test-time attacks whose cost scales unfavorably for the attacker. Because every gradient component must be inferred from repeated circuit executions under any unbiased gradient-estimation rule, white-box extraction consumes a dimension-dependent measurement budget that measurement grouping cannot remove in expressive circuits. Under stated assumptions, single-step attacks need at least quadratically many shots in the input dimension

d

, growing as

d^{5/2}

under norm-concentration scaling, with a sufficient-budget analysis for iterative attacks via stochastic gradient Langevin dynamics. Simulations up to 784 input dimensions validate the law: the realized total budget is the

d^{5/2}

geometric floor for plateau-mitigated models and grows as

d^{3.00}

for the tested deep circuits, whose gradient norms decay with dimension absent barren-plateau mitigation; folding the measured gradient norm back in recovers the parameter-free

d^{3/2}

shot-noise geometry. Against a matched classical baseline whose attack overhead is dimension-independent (the cheap-gradient principle of automatic differentiation), the quantum gradient cost ratio grows empirically as

d^{3.00}

, so the attacker's relative cost diverges as the model scales. Experiments on a 156-qubit IBM processor (ibm_boston, 4-qubit circuits,

d=12

) reproduce the effect: at matched budgets the device attack tracks the ideal within a few percent, with the high-shot gradient faithful to the exact one. The defense operates precisely when the forward map is classically hard to simulate: only then is a white-box attacker denied the simulate-and-backpropagate shortcut and must pay the measurement cost we quantify.

Bacui Li, Chandra Thapa, Tansu Alpcan +1

Department of Electrical and Electronic Engineering, University of Melbourne, Parkville, Victoria 3010, Australia · CSIRO Data61, Marsfield, NSW 2122, Australia · School of Computing and Information Systems, University of Melbourne, Parkville, Victoria 3010, Australia

Gradient-Based Attacks Gradient Classifier

Jul 7, 2026cs.LG

When Certificates Fail: A Unified Safety Framework for Embedded Neural Interface Models

Formal robustness certificates for embedded neural-interface models can pass while task accuracy collapses: at perturbation budget e=0.25, EEGNet classification accuracy drops by 25.7% under projected-gradient attack while the Lipschitz-style certificate remains valid for all 9 tested subjects. We argue that this gap between mathematical certification and operational safety is one instance of a broader alignment failure in neural interfaces, where training objectives diverge from user welfare. We propose a unified empirical audit framework organized around three such failures: verification insufficiency, in which certificates pass while task behavior degrades; proxy-fidelity divergence, in which task-optimized representations damage neural signal structure (a time-domain auxiliary objective reduces reconstruction MSE by 0.1132 while worsening spectral log-MSE); and latent information exfiltration, in which public-task embeddings retain private attributes (subject identity recoverable at 48.1% versus 6.7% chance). We instantiate the framework on BCI Competition IV 2a and SEED-IV using multiple deep and classical EEG decoders, official session-level validation, null controls, and paired statistical tests. The verification gap persists across EEGNet, CSP+LDA, and FBCSP+LDA, and is therefore architecture-independent. Our results establish that operational safety auditing, not certificate verification alone, is necessary for responsible neural-interface deployment.

Jasmeet Singh Bindra

IKSMHA Center, IIT Mandi

Neural Network Verification Brain-Computer Interface Certification Certificates Neuroflex Gradient-Based Attacks

Jul 2, 2026cs.AI

Safety Targeted Embedding Exploit via Refinement

Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training. To study this phenomenon, we introduce STEER (Safety Targeted Embedding Exploit via Refinement), a gradient-guided attack that identifies words contributing most strongly to the model's refusal behavior and iteratively translates them into low-resource languages to suppress refusal while preserving harmful intent. Across six open-source 8B-parameter models, STEER achieves attack success rates of up to 93.0% on JailbreakBench and 96.7% on AdvBench, outperforming random code-switching and Greedy Coordinate Gradient (GCG). The resulting prompts also transfer to GPT-4o-mini, achieving a 35.5% attack success rate without requiring access to the target model, suggesting that the underlying weakness is not specific to a single architecture. These findings demonstrate that safety mechanisms aligned primarily on English cannot be assumed to generalize across multilingual inputs. We argue that improving multilingual safety requires broader coverage during alignment and mechanisms that explicitly detect and abstain on out-of-distribution inputs.

Joshua Adrian Cahyono

Nanyang Technological University, Singapore.

Multilingual Safety Large Language Model Safety Multilingual Language Models Gradient-Based Attacks Exploitation Refinement+1

Jul 2, 2026cs.CR

Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cybersecurity Classifiers

Adversarial attacks on cybersecurity classifiers pose a dual threat: degrading predictions and destabilising the SHAP-based explanations that security analysts rely on to understand and triage alerts. We extend our prior MLP conference study to Random Forest and XGBoost across four tabular security datasets (phishing URLs, UNSW-NB15, NF-ToN-IoT, HIKARI-2021), evaluating five attacks including three black-box methods applicable to non-differentiable tree models. We introduce the Explainability Stability Index (ESI), a scalar metric computed from TreeSHAP attribution drift under adversarial perturbation, reported on the same [0,1] scale as the Robustness Index (RI). A key finding is that gradient-based black-box attacks (ZOO) produce degenerate results against XGBoost (apparent RI ~0.98) due to piecewise-constant prediction surfaces, while score-based Square Attack reveals genuine vulnerability (RI ~0.36). These degenerate perturbations still drive substantial attribution drift: XGBoost ESI ~0.06-0.16 despite near-perfect ZOO robustness, versus 0.14-0.29 for RF, showing that prediction robustness and explanation stability are distinct axes requiring joint measurement. A two-axis framework (gradient dependence, query efficiency) explains the observed attack ranking and yields practical guidance for tree ensemble evaluation. A step-size ablation explains a counterintuitive PGD anomaly on z-score normalised tabular data.

Mona Rajhans, Vishal Khawarey

Palo Alto Networks, Santa Clara, CA, USA · Quicken Inc., Menlo Park, CA, USA

Gradient-Based Attacks Robustness Verification Explainability

Jun 24, 2026cs.LG

Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks

As graph neural networks (GNNs) become standard tools for critical tasks in circuit design and analysis, their security and privacy risks require careful attention. Here, we present the first comprehensive evaluation of gradient leakage attacks (GLAs) on GNNs in circuit-design and hardware-security tasks, a practical threat that has been largely overlooked. We assess state-of-the-art (SOTA) GNNs, including GraphSAGE, GCN, GIN, and GAT, trained on standard netlist benchmarks (ISCAS'85, EPFL, and TrustHub), for their fundamental vulnerability to GLAs. We find that GLAs can expose sensitive information, such as gate types and distinctive properties of hardware Trojans, which may assist adversaries in analyzing logic locking schemes or evading Trojan detection mechanisms. Our analysis shows that these risks are influenced by architectural features, with attention mechanisms (GAT) exacerbating leakage, while injective aggregation (GIN) provides comparatively stronger resilience. We further evaluate several SOTA defense techniques, including differential privacy, gradient clipping, secure aggregation, model compression with quantization, and adversarial training. We find that these techniques improve resilience only in specific settings and can also compromise model performance. Overall, our work provides key insights toward privacy-preserving GNNs and highlights the need for more robust and efficient defenses. We release our full methodology and artifacts.

Rupesh Raj Karn, Johann Knechtel, Ozgur Sinanoglu

Center for Cyber Security, New York University, Abu Dhabi, UAE.

Gradient-Based Attacks Graph Neural Networks Leakage Gradient Malware

Jun 16, 2026cs.CR

TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization

Federated learning allows multiple clients to jointly train a shared model by sending gradient updates to a central server while keeping raw inputs local. However, prior gradient inversion attacks show that these updates can reveal enough information to reconstruct client inputs. Existing attacks on transformers either optimize dummy inputs to match the true client updates, which is costly and unstable for modern models, or exploit the low rank of attention gradients to identify a subspace containing the true layer embeddings, followed by a discrete membership test for candidate tokens. However, this token test is brittle under numerical noise, i.e., from quantization or Differential Privacy (DP), and scales poorly for encoder models with non-causal attention. We introduce TIGER, a continuous gradient inversion attack that turns this subspace signal into a differentiable objective. Instead of searching over tokens or matching full gradients, TIGER directly optimizes token embeddings to minimize their distance to the subspace. Our experiments demonstrate that on encoder-only models, TIGER substantially improves both reconstruction quality and runtime over existing attacks, while on decoder models, TIGER is more robust than prior subspace-based attacks, enabling the first successful reconstructions in DP-defended federated learning settings.

William Kalikman, Ivo Petrov, Dimitar I. Dimitrov +1

ETH Zürich · INSAIT, Sofia University "St. Kliment Ohridski"

Gradient-Based Attacks Federated Learning Transformer Architectures Gradient Subspace

Jun 11, 2026cs.CL

S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP

Despite recent progress in Natural Language Processing (NLP), models remain vulnerable to word substitution attacks. Most existing defenses focus on first order sensitivity and measure how much the output changes when the input is slightly perturbed. However, they ignore how this sensitivity evolves, which is described by curvature. When gradients vary sharply, models can still fail. This paper introduces the Smooth Growth Bound Tensor (S-GBT), a second order method that bounds the Hessian element-wise, for which we provide formal theoretical proofs on the resulting robustness bounds. A regularization term is added during training to minimize these bounds. This yields tighter certified robustness against word substitution attacks. The change in the output under word substitution is bounded by both a linear term and a quadratic term. S-GBT is derived for two architectures: Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN). The method is integrated directly into the training objective. Its effectiveness is evaluated on multiple benchmark datasets. The results show that combining first and second order regularization improves certified robust accuracy by up to 23.4% compared to prior methods, while clean accuracy remains competitive. These findings indicate that controlling both the gradient and its variation is a promising direction for building more robust models.

Mohammed Bouri, Mohammed Erradi, Adnane Saoud

College of Computing, Mohammed VI Polytechnic University, Morocco · CID Development, Morocco · ENSIAS, University Mohamed V of Rabat, Morocco

Gradient-Based Attacks Robustness Verification Natural Language Processing

Jun 10, 2026cs.LG

Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization

Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently optimize adversarial perturbations. To address this, we investigate whether reinforcement learning (RL) training can disrupt the gradient structure used by attackers by training image classifiers with policy-gradient objectives and epsilon-greedy exploration. Through systematic experiments across CIFAR-10, CIFAR-100, and ImageNet-100 with multiple architectures, we find that RL-trained classifiers significantly disrupt gradient-based adversarial optimization. To explain this, we conduct a comprehensive mechanism analysis using loss landscape visualization, static and dynamic gradient indicators, and predictive entropy. Our analysis reveals that RL acts as an implicit regularizer, producing models with highly unstable gradient directions and smaller gradient magnitudes. This combination makes each PGD step both unreliable in direction and limited in magnitude, causing gradient-based attacks to fail within practical iteration budgets. We further show that combining RL with adversarial training (RL-adv) provides a dual-layer defense operating at two complementary levels: RL degrades gradient information available to attackers (gradient-level defense), while adversarial training strengthens decision boundaries (boundary-level defense). RL-adv achieves the highest robustness across all major attack types evaluated, including gradient-based (PGD, AutoAttack), transfer-based, and query-based attacks, outperforming SL-adv by a significant margin. These findings identify RL-induced gradient disruption as a complementary robustness mechanism and motivate future research on hybrid SL-RL training schedules that combine SL's efficiency with RL's gradient-regularization properties.

Xinhai Zou, Chang Zhao, Alireza Aghabagherloo +3

COSIC, KU Leuven · Leuven, Belgium · Imec +1

Gradient-Based Attacks Adversarial Training Offline Reinforcement Learning LLM Defense Mechanisms

May 31, 2026cs.LG

CEAR: Certified Ensemble Adversarial Robustness in DNNs

Deep Neural Networks (DNNs) are highly susceptible to adversarial perturbations, leading to extensive research on robustness for safety-critical applications. State-of-the-art empirical defense mechanisms improve the robustness of DNNs through the training phase, but still struggle against adaptive white-box attacks. On the other hand, certified defenses offer provable guarantees of robustness within a specified perturbation bound. These guarantees hold regardless of the level of perturbations, even if the attacker is given full knowledge of the model. In this paper, we propose CEAR, an ensemble-based robust method that utilizes a hybrid of empirical and certified defense mechanisms. CEAR trains each network within the ensemble using varying Gaussian noise and temperatures to obfuscate gradients and logits, making the model more resistant to stronger gradient-based attacks. We then use noisy logits and propose two different voting mechanisms to further improve robustness. Furthermore, we extend randomized smoothing to verify the robustness of ensemble-based classifiers. Our experimental evaluations on MNIST, CIFAR10, and TinyImageNet datasets demonstrate superior certified accuracy on average, increased robustness radius, and decreased transferability compared to baseline methods.

Daniel Sadig, Mohammadreza Maleki, Hamed Karimi +1

Department of Electrical, Computer, and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON, Canada · Vector Institute, Toronto, ON, Canada

Adversarial Training Model-Agnostic Defense Gradient-Based Attacks Ensemble

May 31, 2026cs.LG

Profiling Privacy Preservation Against Gradient Inversion Attacks in Tabular Federated Learning

Federated learning (FL) enables multiple data holders to train machine learning models collaboratively without centralizing raw data, making it useful in privacy sensitive domains such as healthcare and institutional data sharing. FL keeps data local to clients while communicating only model updates, such as gradients or model deltas. Nevertheless, these updates can expose private client data through gradient inversion attacks (GIAs). We study this risk for tabular FL under an honest-but-curious server threat model across FL protocols, client batch sizes, training stages, attacker assumptions, model architectures, and binary classification, multiclass classification, and regression tasks. We use MIMIC-IV and complementary benchmark datasets. Our evaluation distinguishes numerical and categorical recovery, baseline recoverability, feature level recovery, and exact match rate (EMR). We evaluate FedSGD gradients and FedAvg model deltas with an exposure aligned protocol, comparing attacked models after matched client data exposure rather than matched communication rounds. We compare multilayer perceptron (MLP), ResNet, and FT-Transformer models, and isolate architecture effects through an MLP grid over width, depth, activation, normalization, and dropout. The results show that small client batches and updates representing few distinct records are most vulnerable. Larger local batches and stronger aggregation reduce reconstruction but do not eliminate leakage. FT-Transformer is consistently harder to invert than one-hot baselines, while reconstructability also varies substantially within the MLP family. These findings identify architecture as a practical privacy variable in tabular FL. We also show that aggregate reconstruction accuracy can overstate complete record recovery in sparse data, making EMR and baseline comparisons essential.

Ivo Osterberg Nilsson, Maximilian Birr Engvall, Viktor Valadi +1

Department of Computing, Jönköping University, Jönköping, Sweden · Scaleout Systems, Uppsala, Sweden · Department of Information Systems, University of Haifa, Haifa, Israel

Federated Learning Gradient-Based Attacks Privacy

May 21, 2026cs.CR

EnCAgg: Enhanced Clustering Aggregation for Robust Federated Learning against Dynamic Model Poisoning

Federated learning faces increasing threats from model poisoning attacks, which harms its application to improve privacy. Existing defense methods typically rely on fixed thresholds or perform clustering with a fixed number of clusters to distinguish malicious gradients from benign ones. However, these methods are difficult to adapt to dynamic poisoning strategies of malicious clients, and often result in the loss of benign gradients due to the heterogeneity of clients' local datasets. To address these problems, we propose a novel robust aggregation method that leverages a small number of known benign clients as references, enabling accurate identification and filtering of malicious gradients while retaining as many benign gradients as possible, even when the number of malicious clients is unknown and variable. First, we introduce a density-based low-dimensional gradient clustering method, which projects gradients onto the two most divergent dimensions and applies density-based clustering to identify malicious gradients while retaining clustered benign gradients and potentially benign outliers. Second, we design an enhancing clustering low-dimensional gradient generator model, which learns to generate pseudo-gradients aligned with the boundary of the benign cluster. These pseudo-gradients act as bridges to connect sparse benign gradient outliers. Third, we introduce low-dimensional gradient re-clustering that clusters the generated pseudo-gradients together with real gradients to recover benign gradients misclassified as noise points, enabling more benign gradients to participate in aggregation. Extensive experiments on the MNIST, CIFAR-10, and MIND datasets demonstrate that our method exhibits superior fidelity and robustness under dynamic poisoning scenarios.

Tianyun Zhang, Zhen Yang, Haozhao Wang +2

School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876, China · School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China · Department of Electronic Engineering, Tsinghua University, Beijing 100084, China

Federated Learning Gradient-Based Attacks Poisoning Gradient Outliers

May 19, 2026cs.CV

SDM: A Powerful Tool for Evaluating Model Robustness

Gradient-based attacks are important methods for evaluating model robustness. However, since the proposal of APGD, it has been difficult for such methods to achieve significant breakthroughs. To achieve such an effect, we first analyze the issue of "high-loss non-adversarial examples" that degrades attack performance in previous methods, and prove that this issue arises from inappropriate objectives for adversarial example generation. Subsequently, we reconstruct the objective as "maximizing the difference between the non-ground-truth label probability upper bound and the ground-truth label probability", and proposes a novel and powerful gradient-based attack method named Sequential Difference Maximization (SDM). SDM establishes a three-layer optimization framework of "cycle-stage-step". It adopts the negative probability loss function and the Directional Probability Difference Ratio (DPDR) loss function in the initial and subsequent optimization stages, respectively, and approaches the ideal objective of adversarial example generation via stage-wise sequential optimization. Experiments demonstrate that compared with previous state-of-the-art methods, SDM not only achieves stronger attack performance but also exhibits superior cost-effectiveness. The code is available at https://github.com/X-L-Liu/ICML-SDM.

Xinlei Liu, Tao Hu, Jichao Xie +3

Information Engineering University, Zhengzhou, China · Key Laboratory of Cyberspace Endogenous Safety & Security of Henan Province, Zhengzhou, China · Key Laboratory of Cyberspace Security Ministry of Education of China, Zhengzhou, China +1

Gradient-Based Attacks Adversarial Examples Controlling Tool Use

May 16, 2026cs.CV

Compositional Adversarial Training for Robust Visual Watermarking

Robust watermarking is typically trained with random post-processing augmentation, but random sampling under-covers the combinatorial space of realistic attack pipelines and rarely encounters the rare compositions that actually break detection. This leads to unstable training and poor sample efficiency. We instead formulate watermark robustness as a min-max problem over a structured space of compositional transformations. We propose Compositional Adversarial Training (CAT), a plug-in framework that learns a sequential differentiable adversary that observes the current watermarked image and selects an attack family at each step to maximally disrupt message recovery. CAT combines a straight-through Gumbel-Softmax attack selection with entropy regularization, allowing the backward pass to be end-to-end differentiable and aggregate gradient information across attack families, yielding faster, smoother convergence without collapsing to a single attack mode. We evaluate CAT on post-generation watermarks VideoSeal 0.0, VideoSeal 1.0, and PixelSeal and in-generation WMAR under both single-step and two-step attack suites, on in-distribution and multiple out-of-distribution image and video benchmarks. CAT consistently outperforms random-augmentation baselines trained with the same augmentation budget, with the largest gains on hard composed attacks and OOD evaluations; improving overall watermark capacity by up to

63.5\%

in the single-step attack setting and

13.0\%

in the compositional setting. In the autoregressive setting, CAT improves the TPR@FPR

=1\%

by

12\%

on average on difficult geometric transformations. These results show that robust visual watermarking benefits from training against adaptive compositional adversaries rather than independent random corruptions.

Anirudh Satheesh, Michael-Andrei Panaitescu-Liess, Andrew Xu +4

University of Maryland

Watermarks Watermarking Adversarial Training Gradient-Based Attacks

May 14, 2026cs.LG

Fast Adversarial Attacks with Gradient Prediction

Generating adversarial examples at scale is a core primitive for robustness evaluation, adversarial training, and red-teaming, yet even "fast" attacks such as FGSM remain throughput-limited by the cost of a backward pass. We introduce a family of attacks that eliminates the backward pass by predicting the input gradient from forward-pass hidden states via a lightweight linear regression. The approach is motivated by a kernel view of neural networks and is exact in the Neural Tangent Kernel regime, while remaining effective for practical finite-width models. Empirically, our methods recover much of FGSM's attack performance while using only a small fraction of the time, corresponding to a

532\%

increase in throughput. These results suggest gradient prediction as a simple and general route to significantly faster adversarial generation under realistic wall-clock constraints.

Kamil Ciosek, Aleksandr V. Petrov, Nicolò Felicioni +1

Spotify

Gradient-Based Attacks Black-Box Adversarial Attacks Adversarial Examples Neural Tangent Kernel Backward Passes

May 7, 2026cs.LG

Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations

This work studies the robust evaluation of iterative stochastic purification defenses under white-box adversarial attacks. Our key technical insight is that gradient checkpointing makes exact end-to-end gradient computation through long purification trajectories practical by trading additional recomputation for substantially lower memory usage. This enables full-gradient adaptive attacks against diffusion- and Langevin-based purification defenses, where prior evaluations often resort to approximate backpropagation due to memory constraints. These approximations can weaken the attack signal and risk overestimating robustness. In parallel, stochasticity in iterative purification is frequently under-controlled, even though different purification trajectories can substantially change reported robustness metrics. Building on this insight, we introduce a memory-efficient full-gradient evaluation framework for stochastic purification defenses. The framework combines checkpointed backpropagation with evaluation protocols that control stochastic variability, thereby reducing memory bottlenecks while preserving exact gradients. We evaluate diffusion-based purification and Langevin sampling with Energy-Based Models (EBMs), demonstrating that full-gradient attacks uncover vulnerabilities missed by approximate-gradient evaluations. Our framework yields stronger state-of-the-art

\ell_{\infty}

and

\ell_{2}

white-box attacks and further supports probing out-of-distribution robustness. Overall, our results show that exact-gradient evaluation is essential for reliable benchmarking of iterative stochastic defenses.

Yuan Du, Mitchel Hill, HanQin Cai

Department of Statistics and Data Science University of Central Florida Orlando, FL 32816, USA · InnoPeak Technology Palo Alto, CA 94303, USA · Department of Statistics and Data Science Department of Computer Science University of Central Florida Orlando, FL 32816, USA

Gradient-Based Attacks

May 6, 2026cs.CR

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization

Jailbreak attacks on audio language models (ALMs) optimize audio perturbations to elicit unsafe generations, and they typically update the entire waveform densely throughout optimization. In this work, we investigate the necessity of such dense optimization by analyzing the structure of token-aligned gradients in ALMs. We find that gradient energy is highly non-uniform across audio tokens, indicating that only a small subset of token-aligned audio regions dominates the optimization signal. Motivated by this observation, we propose Token-Aware Gradient Optimization (TAGO), which enables sparse jailbreak optimization by retaining only waveform gradients aligned with audio tokens that have high gradient energy, while masking the remaining gradients at each iteration. Across three ALMs, TAGO outperforms baselines, and substantial sparsification preserves strong attack success rates (e.g. on Qwen3-Omni,

\mathrm{ASR}_{l}

remains at 86% with a token retention ratio of 0.25, compared to 87% with full token retention). These results demonstrate that dense waveform updates are largely redundant, and we advocate that future audio jailbreak and safety alignment research should further leverage this heterogeneous token-level gradient structure.

Zheng Fang, Xiaosen Wang, Shenyi Zhang +2

1Wuhan University · 2Huazhong University of Science and Tech · Institute for Math & AI, Wuhan University +2

Large Language Model Jailbreaks Gradient-Based Attacks Jailbreaks Attack-Success Rate

May 5, 2026cs.LG

Graph Reconstruction from Differentially Private GNN Explanations

Regulatory frameworks such as GDPR increasingly require that ML predictions be accompanied by post-hoc explanations, even when raw data and trained models cannot be released. Differential privacy (DP) is the standard mitigation for the residual privacy risk of releasing these explanations. We show that DP is not sufficient: an adversary observing only DP-perturbed GNN explanations can reconstruct hidden graph structure with high accuracy. Our attack, PRIVX, exploits the fact that the Gaussian DP mechanism is a single DDPM forward step at known noise level σ(ε), recasting reconstruction as reverse diffusion conditioned on the corrupted signal, a principled Bayesian denoiser under known DP corruption. We formalise a stratified adversary model parameterised by (M, \hatε, \hatδ, S, ρ) that interpolates between oblivious and oracle attackers, and derive endpoint-matched two-sided bounds on reconstruction AUC. For practitioners, we provide regime-stratified guidance on explainer choice: on homophilic graphs, neighbourhood-aggregating explainers (GraphLIME, GNNExplainer) leak more structure than per-node gradient explainers under the same DP budget; on strongly heterophilic graphs the ordering reverses. We introduce PRIVF as an auxiliary diagnostic sharing the same diffusion backbone to decompose leakage into explainer-induced and intrinsic graph-distribution components. Experiments across seven benchmarks, three DP mechanisms, and three GNN backbones show PRIVX achieves AUC above 0.7 at ε = 5 on five of seven datasets, with the attack succeeding well within typically deployed privacy budgets.

Rishi Raj Sahoo, Jyotirmaya Shivottam, Subhankar Mishra

National Institute of Science Education and Research (NISER), Bhubaneswar, India · Homi Bhabha National Institute, Mumbai, India

Graph Neural Networks Gradient-Based Attacks Explainable AI Methods

May 2, 2026cs.CR

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection

Representation Engineering analyses often characterize refusal using static directions extracted from terminal or pooled representations. We ask whether this view misses how refusal is constructed across layer-token positions. Using causal tracing, we identify a \textit{Refusal Trajectory}: a sparse upstream activation pattern that often persists even when attacks such as GCG suppress terminal refusal signals. Based on this observation, we propose SALO (Sparse Activation Localization Operator), a lightweight white-box detector that operates on raw hidden-state volumes from a selected layer window. Across Qwen, Llama, and Mistral models, SALO improves jailbreak detection on several attack families under a fixed XSTest-calibrated operating point. We further analyze static RepE-style baselines, ROI sensitivity, adaptive GCG attacks, and encoded-input boundary cases, clarifying both the promise and limitations of refusal-trajectory monitoring.

Xulin Hu, Che Wang, Wei Yang Bryan Lim +2

1Peking University · 2Nanyang Technological University · 3Beijing Jiaotong University

Refusals Jailbreak Attacks Gating Gradient-Based Attacks Model Activations Latent Trajectories

Apr 29, 2026cs.LG

Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry

Safety-aligned language models must refuse harmful requests without broad over-refusal, but it remains unclear how dynamic adversarial fine-tuning changes refusal-control carriers: Kullback--Leibler (KL)-constrained directions or small subspaces that causally modulate refusal without large safe-prompt distribution shifts. We study a 7B backbone under supervised fine-tuning (SFT) and Robust Refusal Dynamic Defense (R2D2), aligning HarmBench, StrongREJECT, and XSTest evaluations with five-anchor geometry measurements, causal interventions, and sparse adaptive stress tests. R2D2 drives fixed-source HarmBench attack success to zero at early checkpoints; however, these checkpoints also exhibit maximal XSTest refusal and fail a benign-utility audit. Later checkpoints partially recover utility-facing behavior while reopening attack success, with adaptive GCG attack success rate rising to 0.415 at step 250 and 0.613 at step 500. Internally, R2D2 preserves a late-layer admissible refusal-control carrier through step 100 and then relocates the best admissible carrier to an early layer; SFT relocates earlier yet remains less robust. Effective rank stays near 1.24, and SFT shows larger principal-angle drift, arguing against both dimensional expansion and drift magnitude as sufficient explanations. Causal interventions support a low-dimensional but utility-coupled carrier. These results support a geometry-reorganization account of R2D2 along a robustness--utility frontier, without establishing adaptive robustness.

Wenhao Lan, Shan Li, Xinhua Lai +4

University of Chinese Academy of Sciences, Beijing, China · Inner Mongolia University of Technology, Inner Mongolia, China · Tsinghua University, Beijing, China +1

Refusals Large Language Model Safety Gradient-Based Attacks

Apr 16, 2026cs.LG

No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learning

Gradient inversion attacks threaten client privacy in federated learning by reconstructing training samples from clients' shared gradients. Gradients aggregate contributions from multiple records and existing attacks may fail to disentangle them, yielding incorrect reconstructions with no intrinsic way to certify success. In vision and language, attackers may fall back on human inspection to judge reconstruction plausibility, but this is far less feasible for numerical tabular records, fueling the impression that tabular data is less vulnerable. We challenge this perception by proposing a verifiable gradient inversion attack (VGIA) that provides an explicit certificate of correctness for reconstructed samples. Our method adopts a geometric view of ReLU leakage: the activation boundary of a fully connected layer defines a hyperplane in input space. VGIA introduces an algebraic, subspace-based verification test that detects when a hyperplane-delimited region contains exactly one record. Once isolation is certified, VGIA recovers the corresponding feature vector analytically and reconstructs the target via a lightweight optimization step. Experiments on tabular benchmarks with large batch sizes demonstrate exact record and target recovery in regimes where existing state-of-the-art attacks either fail or cannot assess reconstruction fidelity. Compared to prior geometric approaches, VGIA allocates hyperplane queries more effectively, yielding faster reconstructions with fewer attack rounds.

Francesco Diana, Chuan Xu, André Nusser +1

Université Côte d’Azur, France · Inria, France · CNRS, France +1

Gradient-Based Attacks Federated Learning Reconstruction Fidelity Systemverilog Assertions

Feb 6, 2026cs.LG

Temperature Scaling Attack Disrupting Model Confidence in Federated Learning

Predictive confidence serves as a foundational control signal in mission-critical systems, directly governing risk-aware logic such as escalation, abstention, and conservative fallback. While prior federated learning attacks predominantly target accuracy or implant backdoors, we identify confidence calibration as a distinct attack objective. We present the Temperature Scaling Attack (TSA), a training-time attack that degrades calibration while preserving accuracy. By injecting temperature scaling with learning rate-temperature coupling during local training, TSA shifts model confidence while keeping predictive accuracy and common optimization signals close to benign training. We provide a convergence analysis under non-IID settings, showing that the coupling controls the primary update scale while leaving a bounded temperature-induced residual, yielding the standard non-convex FL convergence structure with an additional residual term. Across three benchmarks, TSA substantially shifts calibration (e.g., 145% error increase on CIFAR-100) with <2% accuracy change, and remains effective under robust aggregation and post-hoc calibration defenses. Case studies further show up to a 7.2x increase in missed verifications in healthcare and severe confidence-gating failures in autonomous driving, even when accuracy is unchanged. Overall, our results establish calibration integrity as a critical attack surface in federated learning.

Kichang Lee, Jaeho Jin, JaeYeon Park +2

Yonsei University · Dankook University

Federated Learning Gradient-Based Attacks Log-Ratio-Based Gaussian Trust Weight Confidence Calibration

Jan 21, 2026cs.LG

HyperNet-Adaptation for Diffusion-Based Test Case Generation

The increasing deployment of deep learning systems requires systematic evaluation of their reliability in real-world scenarios. Traditional gradient-based adversarial attacks introduce small perturbations that rarely correspond to realistic failures and mainly assess robustness rather than functional behavior. Generative test generation methods offer an alternative but are often limited to simple datasets or constrained input domains. Although diffusion models enable high-fidelity image synthesis, their computational cost and limited controllability restrict their applicability to large-scale testing. We present HyNeA, a generative testing method that enables direct and efficient control over diffusion-based generation. HyNeA provides dataset-free controllability through hypernetworks, allowing targeted manipulation of the generative process without relying on architecture-specific conditioning mechanisms or dataset-driven adaptations such as fine-tuning. HyNeA employs a distinct training strategy that supports instance-level tuning to identify failure-inducing test cases without requiring datasets that explicitly contain examples of similar failures. This approach enables the targeted generation of realistic failure cases at substantially lower computational cost than search-based methods. Experimental results show that HyNeA improves controllability and test diversity compared to existing generative test generators and generalizes to domains where failure-labeled training data is unavailable.

Oliver Weißl, Vincenzo Riccio, Severin Kacianka +1

Technical University of Munich, Germany · University of Udine, Italy · Independent Researcher, Germany +1

Test Generation Gradient-Based Attacks Hypernetwork Controllability

Oct 13, 2025cs.LG

Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness

Auditing information disclosure across every datapoint during the training of LLMs is challenging. We propose a principled, attack-agnostic approach that uses mutual information to measure what the final model reveals about a datapoint's training membership. We show that this final-model disclosure is upper bounded by the sum of per-iteration gradient disclosures and that, under a reasonable set of assumptions, these gradient disclosures increase with Gradient Uniqueness (GNQ), which measures how distinguishable a datapoint's gradient is relative to other gradients in the batch. While naively computing GNQ requires forming and inverting a

P\times P

matrix for every datapoint (for a model with

P

parameters), we introduce Batch-Space Ghost (BS-Ghost). This efficient algorithm performs all computations in a much smaller batch space and uses ghost kernels to compute GNQ "in-run" for every datapoint in the training corpus, with minimal computational and memory overhead. Our experiments show the following: (i) GNQ predicts MIA vulnerability without the need for shadow models. (ii) Beyond membership disclosure, GNQ predicts the success of reconstruction attacks. (iii) GNQ-guided removal and retraining identify datapoints that causally contribute to disclosure. (iv) GNQ outperforms counterfactual memorization in text extraction and common-knowledge discrimination without the need for additional model training. (v) For data attribution, GNQ-guided filtering reduces emergent misalignment in Qwen2.5-7B more than baselines. Further, GNQ attributes 1000 datapoints in 17 seconds---roughly

70\times

faster than the baselines. (vi) GNQ explains how training choices affect training-set disclosure and captures how per-datapoint disclosure emerges during training.

Sleem Abdelghafar, Maryam Aliakbarpour, Christopher Jermaine

Rice University Houston, USA

Gradient-Based Attacks Membership Inference Attacks Disclosures Gradient Component Gradient Model Auditing

Oct 3, 2025cs.CR

NonTextual Target Attack

Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses. However, restricting the objective as inducing fixed targets inherently constrains the adversarial search space, limiting the overall attack efficacy. Furthermore, existing methods typically require numerous optimization iterations to fulfill the large gap between the fixed target and the original LLM output, resulting in low attack efficiency. To overcome these limitations, we propose NonTextual Target Attack (NTA), the first gradient-based attack that relies on a non-textual constrained objective to maximize the unsafety probability of the LLM output, without enforcing any response patterns. For tractable optimization, we further decompose this objective into two constrained sub-objectives, which can be approximated by two differentiable unconstrained losses, to iteratively optimize the response and the adversarial prompt in the neighborhood of the original prompt, with a theoretical analysis to validate the decomposition. In contrast to existing attacks, NTA first realizes gradient-based prompt optimization on a non-textual target and significantly expands the attack space, enabling more flexible and efficient exploration of LLM vulnerabilities. Extensive evaluations show that \textsc{NTA} achieves an average attack success rate of 96.8% against recent safety-aligned LLMs with only 100 optimization iterations on AdvBench, outperforming state-of-the-art gradient-based attacks by over 40%.

Xinzhe Huang, Wenjing Hu, Tianhang Zheng +6

State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou 310007, China · Hangzhou High-Tech Zone, Binjiang Institute of Blockchain and Data Security, Hangzhou 310053, China · School of Cyberspace Security, Nanjing University of Science and Technology, Nanjing 210094, China +3

Attacker Large Language Model Gradient-Based Attacks Jailbreak Attacks

Jul 3, 2025cs.CR

Meta-SecAlign: Training LLMs against Prompt Injection for Robust Agents

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to AI agents. By fine-tuning on simulated prompt injections, SecAlign, a leading open defense, reports LLMs with good test-time robustness and negligible benign utility drop. By scaling up training and evaluations, however, we find that SecAlign actually suffers from significant utility degradation, especially in agentic tasks where the threat of prompt injection is prominent. Motivated by this, we propose Meta-SecAlign for utility-preserving defense by (1) randomized injection position during training to avoid shortcut learning and (2) self-generated responses as high-quality in-distribution training labels. Across general knowledge, instruction following, and agentic workflows (on tool-calling and web-navigation), Meta-SecAlign maintains almost all the undefended LLM's utility while achieving better overall security than SecAlign against various static and GCG adaptive attacks. Experiments use Llama-3.1-8B, Llama-3.3-70B, Llama-4-Scout, Qwen3-4B, and Qwen3.6-27B on 6 prompt injection benchmarks including AgentDojo, InjecAgent, WASP, and SEP. Below are links for the code (https://github.com/facebookresearch/Meta_SecAlign), Meta-SecAlign-70B (https://huggingface.co/facebook/Meta-SecAlign-70B), and Meta-SecAlign-8B (https://huggingface.co/facebook/Meta-SecAlign-8B) models.

Sizhe Chen, Arman Zharmagambetov, David Wagner +1

FAIR at Meta · UC Berkeley

Indirect Prompt Injection Gradient-Based Attacks Prompt Engineering Value Alignment

Dec 17, 2024cs.LG

GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning

The increasing demand for data privacy, alongside the benefits of aggregating data from networked devices, has catalyzed the emergence of federated learning (FL). In FL, clients jointly train a global model by sharing gradients computed over private data. While this paradigm eliminates the need to exchange raw data, inference attacks can still be launched to extract sensitive information from gradients. To this end, partial gradient encryption has emerged as a promising design for balancing privacy and efficiency in practical FL systems, as encrypting only the classification-head gradients is believed to prevent known inference attacks while avoiding the high computational cost of encrypting the entire model. However, this design provides a false sense of privacy. By proposing GDBR, we show that sharing even a single unencrypted layer of gradients can lead to serious privacy leakage. GDBR is the first attack capable of high-fidelity label recovery with partial access to the gradients. It exploits a vulnerability in a commonly used neural building block, constructs a gradient bridge from the unencrypted layer to the final output layer, and approximates the logits information for accurate inference of private labels. These inferred labels not only reveal sensitive information about a client's private dataset but also serve as a prerequisite for many downstream attacks, such as data reconstruction and membership inference. GDBR brings these threats squarely into scope for FL systems employing partial encryption. In addition to theoretical analysis, extensive experiments demonstrate the severity of the problem across a wide variety of datasets and model architectures, including convolutional and transformer-based networks. Overall, our findings challenge the widespread assumption that encrypting only the output layer suffices for privacy protection.

Rui Zhang, Ka-Ho Chow

HKU Musketeers Foundation Institute of Data Science · The University of Hong Kong · Hong Kong SAR, China +1

Federated Learning Gradient-Based Attacks Homomorphic Encryption

Jan 26, 2022cs.CR

Privacy-Preserving Logistic Regression Training with A Faster Gradient Variant

Training logistic regression over encrypted data has emerged as a prominent approach to addressing security concerns in recent years. In this paper, we introduce an efficient gradient variant, termed the \textit{quadratic gradient}, which is specifically designed for privacy-preserving logistic regression while remaining equally effective in plaintext optimization. By incorporating this quadratic gradient, we enhance Nesterov's Accelerated Gradient (NAG), Adaptive Gradient (AdaGrad), and Adam algorithms. We evaluate these enhanced algorithms across various datasets, with experimental results demonstrating state-of-the-art convergence rates that significantly outperform traditional first-order gradient methods. Furthermore, we apply the enhanced NAG method to implement homomorphic logistic regression training, achieving comparable performance within only four iterations. The proposed quadratic-gradient approach offers a unified framework that synergizes the advantages of first-order gradient methods and second-order Newton-type methods, suggesting broad applicability to diverse numerical optimization tasks.

John Chiang

Privacy-Preserving Machine Learning Gradient-Based Attacks Logistic Regression