社会层面 · safety

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this balance. Existing defenses, such as prompt engineering and safety fine-tuning, often introduce computational overhead, increase inference latency, and lack runtime flexibility. Moreover, overly restrictive safety measures can degrade model utility by causing refusals of benign queries. In this paper, we introduce *Jailbreak Antidote*, a method that enables real-time adjustment of LLM safety preferences by manipulating a sparse subset of the model's internal states during inference. By shifting the model's hidden representations along a safety direction with varying strengths, we achieve flexible control over the safety-utility balance without additional token overhead or inference delays. Our analysis reveals that safety-related information in LLMs is sparsely distributed; adjusting approximately *5\%* of the internal state is as effective as modifying the entire state. Extensive experiments on nine LLMs (ranging from 2 billion to 72 billion parameters), evaluated against ten jailbreak attack methods and compared with six defense strategies, validate the effectiveness and efficiency of our approach. By directly manipulating internal states during reasoning, *Jailbreak Antidote* offers a lightweight, scalable solution that enhances LLM safety while preserving utility, opening new possibilities for real-time safety mechanisms in widely-deployed AI systems.

Aligned LLMs are secure, capable of recognizing and refusing to answer malicious questions. However, the role of internal parameters in maintaining such security is not well understood yet, further these models can be vulnerable to security degradation when subjected to fine-tuning attacks. To address these challenges, our work uncovers the mechanism behind security in aligned LLMs at the parameter level, identifying a small set of contiguous layers in the middle of the model that are crucial for distinguishing malicious queries from normal ones, referred to as "safety layers". We first confirm the existence of these safety layers by analyzing variations in input vectors within the model's internal layers. Additionally, we leverage the over-rejection phenomenon and parameters scaling analysis to precisely locate the safety layers. Building on these findings, we propose a novel fine-tuning approach, Safely Partial-Parameter Fine-Tuning (SPPFT), that fixes the gradient of the safety layers during fine-tuning to address the security degradation. Our experiments demonstrate that the proposed approach can significantly preserve LLM security while maintaining performance and reducing computational resources compared to full fine-tuning.

Large language models (LLMs) achieve state-of-the-art performance on multiple language tasks, yet their safety guardrails can be circumvented, leading to harmful generations. In light of this, recent research on safety mechanisms has emerged, revealing that when safety representations or component are suppressed, the safety capability of LLMs are compromised. However, existing research tends to overlook the safety impact of multi-head attention mechanisms, despite their crucial role in various model functionalities. Hence, in this paper, we aim to explore the connection between standard attention mechanisms and safety capability to fill this gap in the safety-related mechanistic interpretability. We propose an novel metric which tailored for multi-head attention, the Safety Head ImPortant Score (Ships), to assess the individual heads' contributions to model safety. Base on this, we generalize Ships to the dataset level and further introduce the Safety Attention Head AttRibution Algorithm (Sahara) to attribute the critical safety attention heads inside the model. Our findings show that special attention head has a significant impact on safety. Ablating a single safety head allows aligned model (e.g., Llama-2-7b-chat) to respond to **16$\times\uparrow$** more harmful queries, while only modifying **0.006\%** $\downarrow$ of the parameters, in contrast to the $\sim$ **5\%** modification required in previous studies. More importantly, we demonstrate that attention heads primarily function as feature extractors for safety and models fine-tuned from the same base model exhibit overlapping safety heads through comprehensive experiments. Together, our attribution approach and findings provide a novel perspective for unpacking the black box of safety mechanisms in large models.

LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings where selective responses are essential, such as content moderation or domain-specific assistants. In this paper, we propose Conditional Activation Steering (CAST), which analyzes LLM activation patterns during inference to selectively apply or withhold activation steering based on the input context. Our method is based on the observation that different categories of prompts activate distinct patterns in the model's hidden states. Using CAST, one can systematically control LLM behavior with rules like "if input is about hate speech or adult content, then refuse" or "if input is not about legal advice, then refuse." This allows for selective modification of responses to specific content while maintaining normal responses to other content, all without requiring weight optimization. We release an open-source implementation of our framework.

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While the large dimensionality of input token space makes it inevitable to find *adversarial* prompts that can jailbreak these models, we aim to evaluate whether safety fine-tuned LLMs are safe against *natural* prompts which are semantically related to toxic seed prompts that elicit safe responses after alignment. We surprisingly find that popular aligned LLMs such as GPT-4 can be compromised using naive prompts that are NOT even crafted with an objective of jailbreaking the model. Furthermore, we empirically show that given a seed prompt that elicits a toxic response from an unaligned model, one can systematically generate several semantically related *natural* prompts that can jailbreak aligned LLMs. Towards this, we propose a method of *Response Guided Question Augmentation (ReG-QA)* to evaluate the generalization of safety aligned LLMs to natural prompts, that first generates several toxic answers given a seed question using an unaligned LLM (Q to A), and further leverages an LLM to generate questions that are likely to produce these answers (A to Q). We interestingly find that safety fine-tuned LLMs such as GPT-4o are vulnerable to producing natural jailbreak *questions* from unsafe content (without denial) and can thus be used for the latter (A to Q) step. We obtain attack success rates that are comparable to/ better than leading adversarial attack methods on the JailbreakBench leaderboard, while being significantly more stable against defenses such as Smooth-LLM and Synonym Substitution, which are effective against existing all attacks on the leaderboard.

The current paradigm for safety alignment of large language models (LLMs) follows a _one-size-fits-all_ approach: the model refuses to interact with any content deemed unsafe by the model provider. This approach lacks flexibility in the face of varying social norms across cultures and regions. In addition, users may have diverse safety needs, making a model with _static_ safety standards too restrictive to be useful, as well as too costly to be re-aligned. We propose _Controllable Safety Alignment_ (CoSA), a framework designed to adapt models to diverse safety requirements without re-training. Instead of aligning a fixed model, we align models to follow _safety configs_—free-form natural language descriptions of the desired safety behaviors—that are provided as part of the system prompt. To adjust model safety behavior, authorized users only need to modify such safety configs at inference time. To enable that, we propose CoSAlign, a data-centric method for aligning LLMs to easily adapt to diverse safety configs. Furthermore, we devise a novel controllability evaluation protocol that considers both helpfulness and configured safety, summarizing them into CoSA-Score, and construct CoSApien, a _human-authored_ benchmark that consists of real-world LLM use cases with diverse safety requirements and corresponding evaluation prompts. We show that CoSAlign leads to substantial gains of controllability over strong baselines including in-context alignment. Our framework encourages better representation and adaptation to pluralistic human values in LLMs, and thereby increasing their practicality.

Algorithmic predictions are increasingly informing societal resource allocations by identifying individuals for targeting. Policymakers often build these systems with the assumption that by gathering more observations on individuals, they can improve predictive accuracy and, consequently, allocation efficiency. An overlooked yet consequential aspect of prediction-driven allocations is that of timing. The planner has to trade off relying on earlier and potentially noisier predictions to intervene before individuals experience undesirable outcomes, or they may wait to gather more observations to make more precise allocations. We examine this tension using a simple mathematical model, where the planner collects observations on individuals to improve predictions over time. We analyze both the ranking induced by these predictions and optimal resource allocation. We show that though individual prediction accuracy improves over time, counter-intuitively, the average ranking loss can worsen. As a result, the planner's ability to improve social welfare can decline. We identify inequality as a driving factor behind this phenomenon. Our findings provide a nuanced perspective and challenge the conventional wisdom that it is preferable to wait for more accurate predictions to ensure the most efficient allocations.

Vulnerability of Frontier language models to misuse has prompted the development of safety measures like filters and alignment training seeking to ensure safety through robustness to adversarially crafted prompts. We assert that robustness is fundamentally insufficient for ensuring safety goals due to inferential threats from dual-intent queries, with current defenses and evaluations failing to account for these risks. To quantify these risks, we introduce a new safety evaluation framework based on $\textit{impermissible information leakage}$ of model outputs and demonstrate how our proposed question-decomposition attack can extract dangerous knowledge from a censored LLM more effectively than traditional jailbreaking. Underlying our proposed evaluation method is a novel information-theoretic threat model of $\textit{inferential adversaries}$, distinguished from $\textit{security adversaries}$, such as jailbreaks, in that success involves inferring impermissible knowledge from victim outputs as opposed to forcing explicitly impermissible victim outputs. Through our information-theoretic framework, we show that ensuring safety against inferential adversaries requires defenses which bound impermissible information leakage, and, such defenses inevitably incur safety-utility trade-offs.

Black swan events are statistically rare occurrences that carry extremely high risks. A typical view of defining black swan events is heavily assumed to originate from an unpredictable time-varying environments; however, the community lacks a comprehensive definition of black swan events. To this end, this paper challenges that the standard view is incomplete and claims that high-risk, statistically rare events can also occur in unchanging environments due to human misperception of their value and likelihood, which we call as spatial black swan event. We first carefully categorize black swan events, focusing on spatial black swan events, and mathematically formalize the definition of black swan events. We hope these definitions can pave the way for the development of algorithms to prevent such events by rationally correcting human perception.

The safety alignment of current Large Language Models (LLMs) is vulnerable. Simple attacks, or even benign fine-tuning, can jailbreak aligned models. We note that many of these vulnerabilities are related to a shared underlying issue: safety alignment can take shortcuts, wherein the alignment adapts a model's generative distribution primarily over only its very first few output tokens. We unifiedly refer to this issue as shallow safety alignment. In this paper, we present case studies to explain why shallow safety alignment can exist and show how this issue universally contributes to multiple recently discovered vulnerabilities in LLMs, including the susceptibility to adversarial suffix attacks, prefilling attacks, decoding parameter attacks, and fine-tuning attacks. The key contribution of this work is that we demonstrate how this consolidated notion of shallow safety alignment sheds light on promising research directions for mitigating these vulnerabilities. We show that deepening the safety alignment beyond the first few tokens can meaningfully improve robustness against some common exploits. We also design a regularized fine-tuning objective that makes the safety alignment more persistent against fine-tuning attacks by constraining updates on initial tokens. Overall, we advocate that future safety alignment should be made more than just a few tokens deep.

As large language models (LLMs) are increasingly deployed on resource-constrained edge devices, quantization techniques have been widely adopted to reduce model size and computational requirements. However, this process can expose models to new vulnerabilities. In this work, we introduce the Quantization Conditioned Misalignment (Q-Misalign) attack, a novel threat in which safety misalignment remains dormant in a full-precision LLM but becomes exploitable post-quantization. We demonstrate that our Q-Misalign attack effectively bypasses safety mechanisms and enables the generation of harmful content in quantized models while maintaining full-precision performance. Furthermore, we propose a contrastive task vector-based approach to enhance attack durability, ensuring that vulnerabilities persist even after downstream fine-tuning. Experimental results show that Q-Misalign attack significantly increases jailbreak success rates in quantized models, while preserving model utility and safety alignment in full precision. Our findings highlight a critical gap in current LLM safety measures and call for more robust defenses in quantization-aware scenarios.