Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models

• URL: http://arxiv.org/abs/2603.10080v2
• Date: Tue, 17 Mar 2026 08:26:11 GMT
• Title: Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models
• Abstract summary: Large Language Models (LLMs) have the potential to create harmful content.<n>In this study, we propose Amnesia, a lightweight activation-space adversarial attack.<n>Our experiments show that the proposed attack can induce various antisocial behaviors in LLMs.
• Score: 1.4092255915948473
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating sophisticated phishing emails and assisting in writing code of harmful computer viruses. Thus, it is crucial to ensure their safe and responsible response generation. To reduce the risk of generating harmful or irresponsible content, researchers have developed techniques such as reinforcement learning with human feedback to align LLM's outputs with human values and preferences. However, it is still undetermined whether such measures are sufficient to prevent LLMs from generating interesting responses. In this study, we propose Amnesia, a lightweight activation-space adversarial attack that manipulates internal transformer states to bypass existing safety mechanisms in open-weight LLMs. Through experimental analysis on state-of-the-art, open-weight LLMs, we demonstrate that our attack effectively circumvents existing safeguards, enabling the generation of harmful content without the need for any fine-tuning or additional training. Our experiments on benchmark datasets show that the proposed attack can induce various antisocial behaviors in LLMs. These findings highlight the urgent need for more robust security measures in open-weight LLMs and underscore the importance of continued research to prevent their potential misuse.

Related papers

• Friend or Foe: How LLMs' Safety Mind Gets Fooled by Intent Shift Attack [53.34204977366491]
  Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities.<n>In this paper, we introduce ISA (Intent Shift Attack), which obfuscates LLMs about the intent of the attacks.<n>Our approach only needs minimal edits to the original request, and yields natural, human-readable, and seemingly harmless prompts.
  arXiv  Detail & Related papers  (2025-11-01T13:44:42Z)
• Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM [53.79753074854936]
  Large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks.<n>This vulnerability poses significant risks to real-world applications.<n>We propose a novel defensive paradigm called GuidelineLLM.
  arXiv  Detail & Related papers  (2024-12-10T12:42:33Z)
• 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)
• Cognitive Overload Attack:Prompt Injection for Long Context [39.61095361609769]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in performing tasks without needing explicit retraining. This capability, known as In-Context Learning (ICL), exposes LLMs to adversarial prompts and jailbreaks that manipulate safety-trained LLMs into generating undesired or harmful output. We apply the principles of Cognitive Load Theory in LLMs and empirically validate that similar to human cognition, LLMs also suffer from cognitive overload. We show that advanced models such as GPT-4, Claude-3.5 Sonnet, Claude-3 OPUS, Llama-3-70B-Instruct, Gemini-1.0-Pro, and
  arXiv  Detail & Related papers  (2024-10-15T04:53:34Z)
• LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts [88.96201324719205]
  Safety concerns in large language models (LLMs) have gained significant attention due to their exposure to potentially harmful data during pre-training.<n>We identify a new safety vulnerability in LLMs, where seemingly benign prompts, semantically related to harmful content, can bypass safety mechanisms.<n>We introduce a novel attack method, textitActorBreaker, which identifies actors related to toxic prompts within pre-training distribution.
  arXiv  Detail & Related papers  (2024-10-14T16:41:49Z)
• Uncovering Safety Risks of Large Language Models through Concept Activation Vector [13.804245297233454]
  We introduce a Safety Concept Activation Vector (SCAV) framework to guide attacks on large language models (LLMs)<n>We then develop an SCAV-guided attack method that can generate both attack prompts and embedding-level attacks.<n>Our attack method significantly improves the attack success rate and response quality while requiring less training data.
  arXiv  Detail & Related papers  (2024-04-18T09:46:25Z)
• Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
  Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. Our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
  arXiv  Detail & Related papers  (2024-04-16T13:22:54Z)
• Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content [33.99403318079253]
  Even safe text coming from large language models can be turned into potentially dangerous content through Bait-and-Switch attacks. The alarming efficacy of this approach highlights a significant challenge in developing reliable safety guardrails for LLMs.
  arXiv  Detail & Related papers  (2024-02-21T16:46:36Z)
• Learning to Poison Large Language Models for Downstream Manipulation [12.521338629194503]
  This work identifies additional security risks in Large Language Models (LLMs) by designing a new data poisoning attack tailored to exploit the supervised fine-tuning process.<n>We propose a novel gradient-guided backdoor trigger learning (GBTL) algorithm to identify adversarial triggers efficiently.<n>We propose two defense strategies against data poisoning attacks, including in-context learning (ICL) and continuous learning (CL)
  arXiv  Detail & Related papers  (2024-02-21T01:30:03Z)
• The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative [55.08395463562242]
  Multimodal Large Language Models (MLLMs) are constantly defining the new boundary of Artificial General Intelligence (AGI) Our paper explores a novel vulnerability in MLLM societies - the indirect propagation of malicious content.
  arXiv  Detail & Related papers  (2024-02-20T23:08:21Z)
• 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)
• Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations [38.437893814759086]
  Large Language Models (LLMs) have shown remarkable success in various tasks, yet their safety and the risk of generating harmful content remain pressing concerns. We propose the In-Context Attack (ICA) which employs harmful demonstrations to subvert LLMs, and the In-Context Defense (ICD) which bolsters model resilience through examples that demonstrate refusal to produce harmful responses.
  arXiv  Detail & Related papers  (2023-10-10T07:50:29Z)
• On the Risk of Misinformation Pollution with Large Language Models [127.1107824751703]
  We investigate the potential misuse of modern Large Language Models (LLMs) for generating credible-sounding misinformation. Our study reveals that LLMs can act as effective misinformation generators, leading to a significant degradation in the performance of Open-Domain Question Answering (ODQA) systems.
  arXiv  Detail & Related papers  (2023-05-23T04:10:26Z)

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.