arXiv subjects

Erick Galinkin

Publications and source records attributed to Erick Galinkin.

At least 19 recordsLinked to original sources

arXiv2025

NVIDIA Nemotron 3: Efficient and Open Intelligence

We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a Mixture-of-Experts hybrid Mamba-Transformer architecture to provide best-in-class throughput and context lengths of up to 1M tokens. Super and Ultra models are trained with NVFP4 and incorporate LatentMoE, a novel approach that improves model quality. The two larger models also include MTP layers for faster text generation. All Nemotron 3 models are post-trained using multi-environment reinforcement learning enabling reasoning, multi-step tool use, and support granular reasoning budget control. Nano, the smallest model, outperforms comparable models in accuracy while remaining extremely cost-efficient for inference. Super is optimized for collaborative agents and high-volume workloads such as IT ticket automation. Ultra, the largest model, provides state-of-the-art accuracy and reasoning performance. Nano is released together with its technical report and this white paper, while Super and Ultra will follow in the coming months. We will openly release the model weights, pre- and post-training software, recipes, and all data for which we hold redistribution rights.

cs.CL↗

arXiv2025

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 trillion new unique tokens over Nemotron 2, followed by supervised fine tuning and large-scale RL on diverse environments. Nemotron 3 Nano achieves better accuracy than our previous generation Nemotron 2 Nano while activating less than half of the parameters per forward pass. It achieves up to 3.3x higher inference throughput than similarly-sized open models like GPT-OSS-20B and Qwen3-30B-A3B-Thinking-2507, while also being more accurate on popular benchmarks. Nemotron 3 Nano demonstrates enhanced agentic, reasoning, and chat abilities and supports context lengths up to 1M tokens. We release both our pretrained Nemotron 3 Nano 30B-A3B Base and post-trained Nemotron 3 Nano 30B-A3B checkpoints on Hugging Face.

cs.CL↗

arXiv2025

Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models

As inference-time scaling becomes critical for enhanced reasoning capabilities, it is increasingly becoming important to build models that are efficient to infer. We introduce Nemotron-H, a family of 8B and 56B/47B hybrid Mamba-Transformer models designed to reduce inference cost for a given accuracy level. To achieve this goal, we replace the majority of self-attention layers in the common Transformer model architecture with Mamba layers that perform constant computation and require constant memory per generated token. We show that Nemotron-H models offer either better or on-par accuracy compared to other similarly-sized state-of-the-art open-sourced Transformer models (e.g., Qwen-2.5-7B/72B and Llama-3.1-8B/70B), while being up to 3$\times$ faster at inference. To further increase inference speed and reduce the memory required at inference time, we created Nemotron-H-47B-Base from the 56B model using a new compression via pruning and distillation technique called MiniPuzzle. Nemotron-H-47B-Base achieves similar accuracy to the 56B model, but is 20% faster to infer. In addition, we introduce an FP8-based training recipe and show that it can achieve on par results with BF16-based training. This recipe is used to train the 56B model. We are releasing Nemotron-H base model checkpoints with support in Hugging Face and NeMo.

cs.CL↗

arXiv2025

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

We introduce Nemotron-Nano-9B-v2, a hybrid Mamba-Transformer language model designed to increase throughput for reasoning workloads while achieving state-of-the-art accuracy compared to similarly-sized models. Nemotron-Nano-9B-v2 builds on the Nemotron-H architecture, in which the majority of the self-attention layers in the common Transformer architecture are replaced with Mamba-2 layers, to achieve improved inference speed when generating the long thinking traces needed for reasoning. We create Nemotron-Nano-9B-v2 by first pre-training a 12-billion-parameter model (Nemotron-Nano-12B-v2-Base) on 20 trillion tokens using an FP8 training recipe. After aligning Nemotron-Nano-12B-v2-Base, we employ the Minitron strategy to compress and distill the model with the goal of enabling inference on up to 128k tokens on a single NVIDIA A10G GPU (22GiB of memory, bfloat16 precision). Compared to existing similarly-sized models (e.g., Qwen3-8B), we show that Nemotron-Nano-9B-v2 achieves on-par or better accuracy on reasoning benchmarks while achieving up to 6x higher inference throughput in reasoning settings like 8k input and 16k output tokens. We are releasing Nemotron-Nano-9B-v2, Nemotron-Nano12B-v2-Base, and Nemotron-Nano-9B-v2-Base checkpoints along with the majority of our pre- and post-training datasets on Hugging Face.

cs.CL↗

arXiv2025

Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models

The introduction of advanced reasoning capabilities have improved the problem-solving performance of large language models, particularly on math and coding benchmarks. However, it remains unclear whether these reasoning models are more or less vulnerable to adversarial prompt attacks than their non-reasoning counterparts. In this work, we present a systematic evaluation of weaknesses in advanced reasoning models compared to similar non-reasoning models across a diverse set of prompt-based attack categories. Using experimental data, we find that on average the reasoning-augmented models are \emph{slightly more robust} than non-reasoning models (42.51\% vs 45.53\% attack success rate, lower is better). However, this overall trend masks significant category-specific differences: for certain attack types the reasoning models are substantially \emph{more vulnerable} (e.g., up to 32 percentage points worse on a tree-of-attacks prompt), while for others they are markedly \emph{more robust} (e.g., 29.8 points better on cross-site scripting injection). Our findings highlight the nuanced security implications of advanced reasoning in language models and emphasize the importance of stress-testing safety across diverse adversarial techniques.

cs.AI↗

arXiv2025

NLP Security and Ethics, in the Wild

As NLP models are used by a growing number of end-users, an area of increasing importance is NLP Security (NLPSec): assessing the vulnerability of models to malicious attacks and developing comprehensive countermeasures against them. While work at the intersection of NLP and cybersecurity has the potential to create safer NLP for all, accidental oversights can result in tangible harm (e.g., breaches of privacy or proliferation of malicious models). In this emerging field, however, the research ethics of NLP have not yet faced many of the long-standing conundrums pertinent to cybersecurity, until now. We thus examine contemporary works across NLPSec, and explore their engagement with cybersecurity's ethical norms. We identify trends across the literature, ultimately finding alarming gaps on topics like harm minimization and responsible disclosure. To alleviate these concerns, we provide concrete recommendations to help NLP researchers navigate this space more ethically, bridging the gap between traditional cybersecurity and NLP ethics, which we frame as ``white hat NLP''. The goal of this work is to help cultivate an intentional culture of ethical research for those working in NLP Security.

cs.CL↗

arXiv2025

Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities

Large Language Models (LLMs) have become an essential tool in the programmer's toolkit, but their tendency to hallucinate code can be used by malicious actors to introduce vulnerabilities to broad swathes of the software supply chain. In this work, we analyze package hallucination behaviour in LLMs across popular programming languages examining both existing package references and fictional dependencies. By analyzing this package hallucination behaviour we find potential attacks and suggest defensive strategies to defend against these attacks. We discover that package hallucination rate is predicated not only on model choice, but also programming language, model size, and specificity of the coding task request. The Pareto optimality boundary between code generation performance and package hallucination is sparsely populated, suggesting that coding models are not being optimized for secure code. Additionally, we find an inverse correlation between package hallucination rate and the HumanEval coding benchmark, offering a heuristic for evaluating the propensity of a model to hallucinate packages. Our metrics, findings and analyses provide a base for future models, securing AI-assisted software development workflows against package supply chain attacks.

cs.LG↗

arXiv2024

Towards Type Agnostic Cyber Defense Agents

With computing now ubiquitous across government, industry, and education, cybersecurity has become a critical component for every organization on the planet. Due to this ubiquity of computing, cyber threats have continued to grow year over year, leading to labor shortages and a skills gap in cybersecurity. As a result, many cybersecurity product vendors and security organizations have looked to artificial intelligence to shore up their defenses. This work considers how to characterize attackers and defenders in one approach to the automation of cyber defense -- the application of reinforcement learning. Specifically, we characterize the types of attackers and defenders in the sense of Bayesian games and, using reinforcement learning, derive empirical findings about how to best train agents that defend against multiple types of attackers.

cs.CR↗

arXiv2024

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like prompt injection and jailbreaking attempt to elicit responses and actions from these models that are not compliant with the safety, privacy, or content policies of organizations using the model in their application. In order to counter abuse of LLMs for generating potentially harmful replies or taking undesirable actions, LLM owners must apply safeguards during training and integrate additional tools to block the LLM from generating text that abuses the model. Jailbreaking prompts play a vital role in convincing an LLM to generate potentially harmful content, making it important to identify jailbreaking attempts to block any further steps. In this work, we propose a novel approach to detect jailbreak prompts based on pairing text embeddings well-suited for retrieval with traditional machine learning classification algorithms. Our approach outperforms all publicly available methods from open source LLM security applications.

cs.CR↗

arXiv2024

The Price of Pessimism for Automated Defense

The well-worn George Box aphorism ``all models are wrong, but some are useful'' is particularly salient in the cybersecurity domain, where the assumptions built into a model can have substantial financial or even national security impacts. Computer scientists are often asked to optimize for worst-case outcomes, and since security is largely focused on risk mitigation, preparing for the worst-case scenario appears rational. In this work, we demonstrate that preparing for the worst case rather than the most probable case may yield suboptimal outcomes for learning agents. Through the lens of stochastic Bayesian games, we first explore different attacker knowledge modeling assumptions that impact the usefulness of models to cybersecurity practitioners. By considering different models of attacker knowledge about the state of the game and a defender's hidden information, we find that there is a cost to the defender for optimizing against the worst case.

cs.CR↗

arXiv2024

AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts

As Large Language Models (LLMs) and generative AI become more widespread, the content safety risks associated with their use also increase. We find a notable deficiency in high-quality content safety datasets and benchmarks that comprehensively cover a wide range of critical safety areas. To address this, we define a broad content safety risk taxonomy, comprising 13 critical risk and 9 sparse risk categories. Additionally, we curate AEGISSAFETYDATASET, a new dataset of approximately 26, 000 human-LLM interaction instances, complete with human annotations adhering to the taxonomy. We plan to release this dataset to the community to further research and to help benchmark LLM models for safety. To demonstrate the effectiveness of the dataset, we instruction-tune multiple LLM-based safety models. We show that our models (named AEGISSAFETYEXPERTS), not only surpass or perform competitively with the state-of-the-art LLM-based safety models and general purpose LLMs, but also exhibit robustness across multiple jail-break attack categories. We also show how using AEGISSAFETYDATASET during the LLM alignment phase does not negatively impact the performance of the aligned models on MT Bench scores. Furthermore, we propose AEGIS, a novel application of a no-regret online adaptation framework with strong theoretical guarantees, to perform content moderation with an ensemble of LLM content safety experts in deployment

cs.LG↗

arXiv2024

garak: A Framework for Security Probing Large Language Models

As Large Language Models (LLMs) are deployed and integrated into thousands of applications, the need for scalable evaluation of how models respond to adversarial attacks grows rapidly. However, LLM security is a moving target: models produce unpredictable output, are constantly updated, and the potential adversary is highly diverse: anyone with access to the internet and a decent command of natural language. Further, what constitutes a security weak in one context may not be an issue in a different context; one-fits-all guardrails remain theoretical. In this paper, we argue that it is time to rethink what constitutes ``LLM security'', and pursue a holistic approach to LLM security evaluation, where exploration and discovery of issues are central. To this end, this paper introduces garak (Generative AI Red-teaming and Assessment Kit), a framework which can be used to discover and identify vulnerabilities in a target LLM or dialog system. garak probes an LLM in a structured fashion to discover potential vulnerabilities. The outputs of the framework describe a target model's weaknesses, contribute to an informed discussion of what composes vulnerabilities in unique contexts, and can inform alignment and policy discussions for LLM deployment.

cs.CL↗

arXiv2022

Simulation of Attacker Defender Interaction in a Noisy Security Game

In the cybersecurity setting, defenders are often at the mercy of their detection technologies and subject to the information and experiences that individual analysts have. In order to give defenders an advantage, it is important to understand an attacker's motivation and their likely next best action. As a first step in modeling this behavior, we introduce a security game framework that simulates interplay between attackers and defenders in a noisy environment, focusing on the factors that drive decision making for attackers and defenders in the variants of the game with full knowledge and observability, knowledge of the parameters but no observability of the state (``partial knowledge''), and zero knowledge or observability (``zero knowledge''). We demonstrate the importance of making the right assumptions about attackers, given significant differences in outcomes. Furthermore, there is a measurable trade-off between false-positives and true-positives in terms of attacker outcomes, suggesting that a more false-positive prone environment may be acceptable under conditions where true-positives are also higher.

cs.CR↗

arXiv2022

Robustness and Usefulness in AI Explanation Methods

Explainability in machine learning has become incredibly important as machine learning-powered systems become ubiquitous and both regulation and public sentiment begin to demand an understanding of how these systems make decisions. As a result, a number of explanation methods have begun to receive widespread adoption. This work summarizes, compares, and contrasts three popular explanation methods: LIME, SmoothGrad, and SHAP. We evaluate these methods with respect to: robustness, in the sense of sample complexity and stability; understandability, in the sense that provided explanations are consistent with user expectations; and usability, in the sense that the explanations allow for the model to be modified based on the output. This work concludes that current explanation methods are insufficient; that putting faith in and adopting these methods may actually be worse than simply not using them.

cs.LG↗

arXiv2022

Towards a Responsible AI Development Lifecycle: Lessons From Information Security

Legislation and public sentiment throughout the world have promoted fairness metrics, explainability, and interpretability as prescriptions for the responsible development of ethical artificial intelligence systems. Despite the importance of these three pillars in the foundation of the field, they can be challenging to operationalize and attempts to solve the problems in production environments often feel Sisyphean. This difficulty stems from a number of factors: fairness metrics are computationally difficult to incorporate into training and rarely alleviate all of the harms perpetrated by these systems. Interpretability and explainability can be gamed to appear fair, may inadvertently reduce the privacy of personal information contained in training data, and increase user confidence in predictions -- even when the explanations are wrong. In this work, we propose a framework for responsibly developing artificial intelligence systems by incorporating lessons from the field of information security and the secure development lifecycle to overcome challenges associated with protecting users in adversarial settings. In particular, we propose leveraging the concepts of threat modeling, design review, penetration testing, and incident response in the context of developing AI systems as ways to resolve shortcomings in the aforementioned methods.

cs.AI↗

arXiv2021

Evaluating Attacker Risk Behavior in an Internet of Things Ecosystem

In cybersecurity, attackers range from brash, unsophisticated script kiddies and cybercriminals to stealthy, patient advanced persistent threats. When modeling these attackers, we can observe that they demonstrate different risk-seeking and risk-averse behaviors. This work explores how an attacker's risk seeking or risk averse behavior affects their operations against detection-optimizing defenders in an Internet of Things ecosystem. Using an evaluation framework which uses real, parametrizable malware, we develop a game that is played by a defender against attackers with a suite of malware that is parameterized to be more aggressive and more stealthy. These results are evaluated under a framework of exponential utility according to their willingness to accept risk. We find that against a defender who must choose a single strategy up front, risk-seeking attackers gain more actual utility than risk-averse attackers, particularly in cases where the defender is better equipped than the two attackers anticipate. Additionally, we empirically confirm that high-risk, high-reward scenarios are more beneficial to risk-seeking attackers like cybercriminals, while low-risk, low-reward scenarios are more beneficial to risk-averse attackers like advanced persistent threats.

cs.CR↗

arXiv2021

Winning the Ransomware Lottery: A Game-Theoretic Model for Mitigating Ransomware Attacks

Ransomware is a growing threat to individuals and enterprises alike, constituting a major factor in cyber insurance and in the security planning of every organization. Although the game theoretic lens often frames the game as a competition between equals -- a profit maximizing attacker and a loss minimizing defender -- the reality of many situations is that ransomware organizations are not playing a non-cooperative game, they are playing a lottery. The wanton behavior of attackers creates a situation where many victims are hit more than once by ransomware operators, sometimes even by the same group. If defenders wish to combat malware, they must then seek to remove the incentives of it. In this work, we construct an expected value model based on data from actual ransomware attacks and identify three variables: the value of payments, the cost of an attack, and the probability of payment. Using this model, we consider the potential to manipulate these variables to reduce the profit motive associated with ransomware attack. Based on the model, we present mitigations to encourage an environment that is hostile to ransomware operators. In particular, we find that off-site backups and government incentives for their adoption are the most fruitful avenue for combating ransomware.

cs.CR↗

arXiv2021

Who's Afraid of Thomas Bayes?

In many cases, neural networks perform well on test data, but tend to overestimate their confidence on out-of-distribution data. This has led to adoption of Bayesian neural networks, which better capture uncertainty and therefore more accurately reflect the model's confidence. For machine learning security researchers, this raises the natural question of how making a model Bayesian affects the security of the model. In this work, we explore the interplay between Bayesianism and two measures of security: model privacy and adversarial robustness. We demonstrate that Bayesian neural networks are more vulnerable to membership inference attacks in general, but are at least as robust as their non-Bayesian counterparts to adversarial examples.

cs.LG↗