Security Steerability is All You Need

• URL: http://arxiv.org/abs/2504.19521v2
• Date: Tue, 29 Apr 2025 17:22:55 GMT
• Title: Security Steerability is All You Need
• Authors: Itay Hazan, Idan Habler, Ron Bitton, Itsik Mantin,
• Abstract summary: We show that while LLMs cannot protect against ad-hoc application specific threats, they can provide the framework for applications to protect themselves against such threats.<n>Our first contribution is defining Security Steerability - a novel security measure for LLMs, assessing the model's capability to adhere to strict guardrails that are defined in the system prompt.<n>Our second contribution is a methodology to measure the security steerability of LLMs, utilizing two newly-developed datasets.
• Score: 3.475823664889679
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The adoption of Generative AI (GenAI) in various applications inevitably comes with expanding the attack surface, combining new security threats along with the traditional ones. Consequently, numerous research and industrial initiatives aim to mitigate these security threats in GenAI by developing metrics and designing defenses. However, while most of the GenAI security work focuses on universal threats (e.g. manipulating the LLM to generate forbidden content), there is significantly less discussion on application-level security and how to mitigate it. Thus, in this work we adopt an application-centric approach to GenAI security, and show that while LLMs cannot protect against ad-hoc application specific threats, they can provide the framework for applications to protect themselves against such threats. Our first contribution is defining Security Steerability - a novel security measure for LLMs, assessing the model's capability to adhere to strict guardrails that are defined in the system prompt ('Refrain from discussing about politics'). These guardrails, in case effective, can stop threats in the presence of malicious users who attempt to circumvent the application and cause harm to its providers. Our second contribution is a methodology to measure the security steerability of LLMs, utilizing two newly-developed datasets: VeganRibs assesses the LLM behavior in forcing specific guardrails that are not security per se in the presence of malicious user that uses attack boosters (jailbreaks and perturbations), and ReverseText takes this approach further and measures the LLM ability to force specific treatment of the user input as plain text while do user try to give it additional meanings...

Related papers

• 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)
• Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation [4.241100280846233]
  AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication.<n>This paper investigates a critical vulnerability: adversarial attacks targeting the LLM core within AI agents.
  arXiv  Detail & Related papers  (2024-12-05T18:38:30Z)
• Global Challenge for Safe and Secure LLMs Track 1 [57.08717321907755]
  The Global Challenge for Safe and Secure Large Language Models (LLMs) is a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme Office (CRPO) This paper introduces the Global Challenge for Safe and Secure Large Language Models (LLMs), a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme Office (CRPO) to foster the development of advanced defense mechanisms against automated jailbreaking attacks.
  arXiv  Detail & Related papers  (2024-11-21T08:20:31Z)
• Defining and Evaluating Physical Safety for Large Language Models [62.4971588282174]
  Large Language Models (LLMs) are increasingly used to control robotic systems such as drones. Their risks of causing physical threats and harm in real-world applications remain unexplored. We classify the physical safety risks of drones into four categories: (1) human-targeted threats, (2) object-targeted threats, (3) infrastructure attacks, and (4) regulatory violations.
  arXiv  Detail & Related papers  (2024-11-04T17:41:25Z)
• LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks [7.013820690538764]
  We study attacks that exploit the emphfalse negatives of safeguard methods.<n>The malicious attackers could also exploit false positives of safeguards, leading to a denial-of-service (DoS) affecting users.
  arXiv  Detail & Related papers  (2024-10-03T19:07:53Z)
• SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering [56.92068213969036]
  Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions.<n>Recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue.<n>We propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns.
  arXiv  Detail & Related papers  (2024-08-21T10:01:34Z)
• Purple-teaming LLMs with Adversarial Defender Training [57.535241000787416]
  We present Purple-teaming LLMs with Adversarial Defender training (PAD) PAD is a pipeline designed to safeguard LLMs by novelly incorporating the red-teaming (attack) and blue-teaming (safety training) techniques. PAD significantly outperforms existing baselines in both finding effective attacks and establishing a robust safe guardrail.
  arXiv  Detail & Related papers  (2024-07-01T23:25:30Z)
• A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Models [5.077431021127288]
  This paper addresses a gap in current research by focusing on security risks posed by large language models (LLMs) Our work proposes a taxonomy of security risks along the user-model communication pipeline and categorizes the attacks by target and attack type alongside the commonly used confidentiality, integrity, and availability (CIA) triad.
  arXiv  Detail & Related papers  (2023-11-19T20:22:05Z)
• Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications [37.316238236750415]
  Large language models (LLMs) are increasingly deployed as the service backend for LLM-integrated applications. In this work, we consider a setup where the user and LLM interact via an LLM-integrated application in the middle. We identify potential vulnerabilities that can originate from the malicious application developer or from an outsider threat. We develop a lightweight, threat-agnostic defense that mitigates both insider and outsider threats.
  arXiv  Detail & Related papers  (2023-11-07T20:13:05Z)
• Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities [14.684194175806203]
  Large language models (LLMs) can be misused for fraud, impersonation, and the generation of malware. We present a taxonomy describing the relationship between threats caused by the generative capabilities of LLMs, prevention measures intended to address such threats, and vulnerabilities arising from imperfect prevention measures.
  arXiv  Detail & Related papers  (2023-08-24T14:45:50Z)
• 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.