IntentAlign-MiniLM, the authors' 22M-parameter intent-aligned retriever, outperforms much larger embedding models on held-out intent retrieval and yields the best learned-retriever harmful recall across tested guardrails.
Abstract
Scaling laws are usually read as a capability story: lower language-modeling loss yields more useful models. We study a safety consequence of this mechanism in \emph{cross-session decomposition attacks}, where benign-looking subqueries are asked across independent interactions and later recomposed toward a forbidden objective. We formalize this setting as \emph{compositional safety risk} and prove a conditional risk-transfer bound: when the reference environment already contains dispersed evidence for a risky reconstruction, the gap between deployed composed risk and reference composed risk is controlled by the model's excess loss on allowed subqueries. Synthetic withholding experiments show that wider transformers assign lower loss to held-out instructions that never appear verbatim in training but are recoverable from injected supporting facts. A 600-intent pretrained-LLM evaluation shows that larger Qwen3 and Gemma3 family members can yield greater harmful-capability uplift under a fixed decomposition-composition pipeline. As a defense, IntentAlign-MiniLM, our 22M-parameter intent-aligned retriever, outperforms much larger embedding models on held-out intent retrieval and yields the best learned-retriever harmful recall across tested guardrails. Code is available in \href{https://github.com/liaodisen/Cross-Session-Decomposition-Attacks}{our GitHub repository}.
Large language models (LLMs) are increasingly deployed in safety-critical applications, yet jailbreak attacks can conceal harmful intent through role-playing, fictional scenarios, or seemingly benign motivations. Existing inference-time defenses may miss disguised attacks or excessively refuse legitimate requests. We propose SRD-GUARD, a parameter-free, black-box defense framework that exposes concealed intent through semantic rewriting and consensus-based risk assessment. Given an input prompt, SRD-GUARD generates five semantically related rewrites that preserve the underlying objective while removing unnecessary contextual packaging. The original prompt and rewrites are jointly evaluated by multiple independent LLM-based safety scorers on a continuous risk scale. A decision module combines absolute risk thresholds with relative risk changes between the original and rewritten prompts to adaptively intercept, preserve, or warn on requests. We evaluate SRD-GUARD against UNIATTACK, CIPHER, and DeepInception on Llama-3-8B-Uncensored and DeepSeek-V4-Flash using AdvBench and OR-Bench-Hard. SRD-GUARD achieves average DSRs of 91.44% and 100%, with ORRs of 8.00% and 12.00%, respectively. Compared with evaluated baselines, it provides a more favorable DSR--ORR trade-off. Ablation studies show that rewriting exposes concealed harmful intent, joint scoring improves robustness to individual evaluator behavior, and risk-adaptive decision making enables selective handling of ambiguous inputs. These results demonstrate that semantic intent exposure, consensus-based risk assessment, and relative-risk-aware routing provide an effective and selective approach to black-box jailbreak defense. The artifact is available at https://anonymous.4open.science/status/CICD-Guard-D648.
Mixture-of-Experts (MoE) is a scaling architecture for large language models that activates only a small subset of expert modules per token, enabling massive parameter growth with nearly constant computation. Recent Hybrid MoE architecture adds \textit{shared experts} to capture consistently useful representations, further improving stability and generalization. MoE now powers many flagship open-source and commercial models, yet remains vulnerable to adversarial attacks. Specifically, sparse routing introduces a structural vulnerability: MoE safety hinges on which experts are activated, and adversaries can subvert this selection through jailbreak prompts, malicious fine-tuning, and weight-level pruning of safety-critical neurons. Existing defenses primarily focus on hardening the router, but an adversary may still manipulate or bypass the routing trajectory due to the routing process's nondeterministic nature, thereby collapsing the defense. To cope with this problem, we first identify theoretically and empirically that shared expert, an always-activated component containing a small proportion of safety-critical neurons, can overcome the uncertainty of sparsely activated routing path and serve as a router-independent anchor to enhance global safety alignment. Based on this insight, we propose SEAL, a training-time parameter-efficient defense that produces a plug-and-play adapter attached to shared expert, and SEAL++, a variant that adds an orthogonal constraint preserving pre-existing safety subspaces during training. We evaluate SEAL and SEAL++ across six attack scenarios that combine three adversarial inputs (harmful prompting, jailbreak, malicious fine-tuning) with and without neuron pruning. SEAL reduces attack success rate (ASR) by up to 60\%, at a capability cost of at most 1.4\% on a five-benchmark average. Additionally, SEAL can seamlessly integrate with router-level ......
Qingyu Meng, Yiwei Zha, Jiahuan Pei et al.· 0 citations
Retrieval-Augmented Generation (RAG) can ground large language model (LLM) outputs in external evidence, but it also exposes the system to knowledge poisoning. Representative attacks use multiple injected documents or templates that directly assert a target answer. We present ToxicRAG, a one-document-per-target attack that expresses misinformation as a coherent knowledge-update narrative. The generated document first acknowledges the previously accepted answer, introduces fabricated events that appear to invalidate it, and then attributes the attacker-selected answer to a set of purported authorities. An answer-focused self-validation loop optionally revises a candidate when a surrogate language model does not reproduce the target answer. We evaluate the attack on 100 target questions from each of Natural Questions, HotpotQA, and MS-MARCO, using four victim LLMs and four dense retrievers. In the sampled-corpus setting reported in this paper, ToxicRAG obtains ASRs between 0.61 and 0.91 across the twelve dataset--model combinations. It matches or exceeds the strongest evaluated baseline in every combination, with margins ranging from 0 to 11 percentage points. These results show that narrative-form poisoned documents can remain influential under the evaluated RAG configurations and motivate further study of factual consistency and source provenance in RAG systems.
It is proved that, under an honest-majority assumption and a representation-level separation condition, RAGSentinel exactly recovers a poison-free majority-sized context.
Yueyang Quan, Anjun Gao, Yu Xia et al.· 0 citations
A benchmark for this vulnerability in LLM-based resume screening is introduced: 463 job-candidate pairs drawn from a 14-domain corpus, with the evaluated sample covering 13 domains, attacked through a taxonomy of four attack types and four injection positions.
Hong-Lin Mu, Jinghao Liu, Kaiyang Wan et al.· International Journal of Mac...· 3 citations· ⚡1
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains vulnerable to jailbreak attacks. A key challenge is that safety behavior learned in the textual space does not reliably transfer to fused cross-modal representations, leaving multimodal inputs exploitable through latent semantic cues. We propose Text-Anchored Semantic Perturbation Attack (TA-SPA), a black-box jailbreak framework that optimizes transferable perturbations in a text-anchored semantic space. TA-SPA integrates Text-Anchored Semantic Factorization (TASF), which encourages the separation of cross-modal semantic factors from modality-specific residuals, with Semantic-Preserving Augmentation (SPA), which diversifies harmful target anchors while preserving semantic consistency. Experiments show strong attack effectiveness and transfer to commercial MLLMs, with competitive performance under representative defenses. Additional controls and probing support the intended factorization without implying perfect disentanglement, motivating representation-level safety alignment beyond input-level filtering.
Wenyun Li, Guiping Cao, Xiangyuan Lan et al.· 0 citations
