Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks

• URL: http://arxiv.org/abs/2507.02735v2
• Date: Mon, 10 Nov 2025 16:30:10 GMT
• Title: Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks
• Authors: Sizhe Chen, Arman Zharmagambetov, David Wagner, Chuan Guo,
• Abstract summary: We develop Meta SecAlign, the first fully open-source LLM with built-in model-level defense.<n>We perform the most comprehensive evaluation to date on 9 utility benchmarks and 7 security benchmarks on general knowledge, instruction following, and agentic.<n>Our best model -- Meta-SecAlign-70B -- establishes a new frontier of utility-security trade-off for open-source LLMs.
• Score: 15.266469377135978
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prompt injection attack has been listed as the top-1 security threat to LLM-integrated applications, which interact with external environment data for complex tasks. The untrusted data may contain an injected prompt trying to arbitrarily manipulate the system. Model-level prompt injection defenses have shown strong effectiveness, but are currently deployed into commercial-grade models in a closed-source manner. We believe open-source secure models are needed by the AI security community, where co-development of attacks and defenses through open research drives scientific progress in mitigating prompt injection attacks. To this end, we develop Meta SecAlign, the first fully open-source LLM with built-in model-level defense that achieves commercial-grade performance, powerful enough for complex agentic tasks. We provide complete details of our training recipe, an improved version of the SOTA SecAlign defense. We perform the most comprehensive evaluation to date on 9 utility benchmarks and 7 security benchmarks on general knowledge, instruction following, and agentic workflows. Results show that Meta SecAlign, despite being trained on generic instruction-tuning samples only, surprisingly confers security in unseen downstream tasks, including tool-calling and web-navigation, in addition to general instruction-following. Our best model -- Meta-SecAlign-70B -- establishes a new frontier of utility-security trade-off for open-source LLMs. Even compared to closed-course commercial models such as GPT-5, our model is much securer than most of them. 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.

Related papers

• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection [45.69684471143409]
  VulnLLM-R is theemphfirst specialized reasoning LLM for vulnerability detection.<n>We train a reasoning model with seven billion parameters.<n>We show that VulnLLM-R has superior effectiveness and efficiency than SOTA static analysis tools.
  arXiv  Detail & Related papers  (2025-12-08T13:06:23Z)
• Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools [10.086284534400658]
  Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools.<n>We identify this as a new and stealthy threat surface that allows malicious tools to be preferentially selected by LLM agents.<n>We propose a black-box in-context learning framework that generates highly attractive but syntactically and semantically valid tool metadata.
  arXiv  Detail & Related papers  (2025-08-04T06:38:59Z)
• Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems [18.039444159491733]
  Large Language Models (LLMs) deployed in enterprise settings face novel security challenges.<n>One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually extract confidential data.<n>We present a comprehensive study of multi-stage prompt inference attacks in an enterprise LLM context.
  arXiv  Detail & Related papers  (2025-07-21T13:38:12Z)
• A Survey on Model Extraction Attacks and Defenses for Large Language Models [55.60375624503877]
  Model extraction attacks pose significant security threats to deployed language models.<n>This survey provides a comprehensive taxonomy of extraction attacks and defenses, categorizing attacks into functionality extraction, training data extraction, and prompt-targeted attacks.<n>We examine defense mechanisms organized into model protection, data privacy protection, and prompt-targeted strategies, evaluating their effectiveness across different deployment scenarios.
  arXiv  Detail & Related papers  (2025-06-26T22:02:01Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• Defeating Prompt Injections by Design [79.00910871948787]
  CaMeL is a robust defense that creates a protective system layer around the Large Language Models.<n>To operate, CaMeL explicitly extracts the control and data flows from the (trusted) query.<n>To further improve security, CaMeL uses a notion of a capability to prevent the exfiltration of private data over unauthorized data flows.
  arXiv  Detail & Related papers  (2025-03-24T15:54:10Z)
• Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks [88.84977282952602]
  A high volume of recent ML security literature focuses on attacks against aligned large language models (LLMs)<n>In this paper, we analyze security and privacy vulnerabilities that are unique to LLM agents.<n>We conduct a series of illustrative attacks on popular open-source and commercial agents, demonstrating the immediate practical implications of their vulnerabilities.
  arXiv  Detail & Related papers  (2025-02-12T17:19:36Z)
• SecAlign: Defending Against Prompt Injection with Preference Optimization [52.48001255555192]
  Adversarial prompts can be injected into external data sources to override the system's intended instruction and execute a malicious instruction.<n>We propose a new defense called SecAlign based on the technique of preference optimization.<n>Our method reduces the success rates of various prompt injections to 10%, even against attacks much more sophisticated than ones seen during training.
  arXiv  Detail & Related papers  (2024-10-07T19:34:35Z)
• Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning [25.153530916709002]
  We introduce a novel secure-tuning strategy called SWAT.<n>By analyzing how module-level parameters affect the security feature space drift, we identify a robust subset of modules, termed Mods_Rob.<n>Our SWAT strategy begins by warming up Mods_Rob to capture low-level features with minimal security risks, followed by training all parameters to achieve optimal task performance.
  arXiv  Detail & Related papers  (2024-10-06T15:34:04Z)
• Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models [8.024771725860127]
  Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. We introduce a novel scalable jailbreak attack that preempts the activation of an LLM's safety policies by occupying its computational resources.
  arXiv  Detail & Related papers  (2024-10-05T15:10:01Z)
• Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents [32.62654499260479]
  We introduce Agent Security Bench (ASB), a framework designed to formalize, benchmark, and evaluate the attacks and defenses of LLM-based agents.<n>Based on ASB, we benchmark 10 prompt injection attacks, a memory poisoning attack, a novel Plan-of-Thought backdoor attack, 4 mixed attacks, and 11 corresponding defenses.<n>Our benchmark results reveal critical vulnerabilities in different stages of agent operation, including system prompt, user prompt handling, tool usage, and memory retrieval.
  arXiv  Detail & Related papers  (2024-10-03T16:30:47Z)
• BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models [27.59116619946915]
  Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks.<n>BackdoorLLM is the first comprehensive benchmark for systematically evaluating backdoor threats in text-generation LLMs.<n>BackdoorLLM provides: (i) a unified repository of benchmarks with a standardized training and evaluation pipeline; (ii) a diverse suite of attack modalities, including data poisoning, weight poisoning, hidden-state manipulation, and chain-of-thought hijacking; (iii) over 200 experiments spanning 8 distinct attack strategies, 7 real-
  arXiv  Detail & Related papers  (2024-08-23T02:21:21Z)
• ShieldGemma: Generative AI Content Moderation Based on Gemma [49.91147965876678]
  ShieldGemma is a suite of safety content moderation models built upon Gemma2. Models provide robust, state-of-the-art predictions of safety risks across key harm types.
  arXiv  Detail & Related papers  (2024-07-31T17:48:14Z)
• Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks [59.46556573924901]
  This paper introduces Defensive Prompt Patch (DPP), a novel prompt-based defense mechanism for large language models (LLMs)<n>Unlike previous approaches, DPP is designed to achieve a minimal Attack Success Rate (ASR) while preserving the high utility of LLMs.<n> Empirical results conducted on LLAMA-2-7B-Chat and Mistral-7B-Instruct-v0.2 models demonstrate the robustness and adaptability of DPP.
  arXiv  Detail & Related papers  (2024-05-30T14:40:35Z)
• Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities [1.0974825157329373]
  This paper provides a comprehensive review of the future of cybersecurity through Generative AI and Large Language Models (LLMs)<n>We explore LLM applications across various domains, including hardware design security, intrusion detection, software engineering, design verification, cyber threat intelligence, malware detection, and phishing detection.<n>We present an overview of LLM evolution and its current state, focusing on advancements in models such as GPT-4, GPT-3.5, Mixtral-8x7B, BERT, Falcon2, and LLaMA.
  arXiv  Detail & Related papers  (2024-05-21T13:02:27Z)
• AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting [54.931241667414184]
  We propose textbfAdaptive textbfShield Prompting, which prepends inputs with defense prompts to defend MLLMs against structure-based jailbreak attacks. Our methods can consistently improve MLLMs' robustness against structure-based jailbreak attacks.
  arXiv  Detail & Related papers  (2024-03-14T15:57:13Z)
• Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models [79.0183835295533]
  We introduce the first benchmark for indirect prompt injection attacks, named BIPIA, to assess the risk of such vulnerabilities.<n>Our analysis identifies two key factors contributing to their success: LLMs' inability to distinguish between informational context and actionable instructions, and their lack of awareness in avoiding the execution of instructions within external content.<n>We propose two novel defense mechanisms-boundary awareness and explicit reminder-to address these vulnerabilities in both black-box and white-box settings.
  arXiv  Detail & Related papers  (2023-12-21T01:08:39Z)
• A Comprehensive Survey of Attack Techniques, Implementation, and Mitigation Strategies in Large Language Models [0.0]
  This article explores two attack categories: attacks on models themselves and attacks on model applications. The former requires expertise, access to model data, and significant implementation time. The latter is more accessible to attackers and has seen increased attention.
  arXiv  Detail & Related papers  (2023-12-18T07:07:32Z)
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection [64.67495502772866]
  Large Language Models (LLMs) are increasingly being integrated into various applications. We show how attackers can override original instructions and employed controls using Prompt Injection attacks. We derive a comprehensive taxonomy from a computer security perspective to systematically investigate impacts and vulnerabilities.
  arXiv  Detail & Related papers  (2023-02-23T17:14:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.