Language Model Security Database

Inference-time Personally Identifiable Information (PII) leakage is significantly amplified when using Chain-of-Thought (CoT) prompting or reasoning-enabled Large Language Models (LLMs). When an attacker or user elicits step-by-step reasoning or utilizes models with native "thinking" token budgets, sensitive context data provided in the prompt is directly resurfaced into intermediate reasoning steps or the final output. This bypasses output-level privacy policies instructing the model not to…

An "in-content harm" vulnerability exists in safety-aligned Large Language Models (LLMs) where task-level alignment mechanisms fail to evaluate the safety of user-provided external data. Attackers can bypass safety guardrails by embedding policy-violating text (e.g., violence, self-harm, explicit content) within the payload of a seemingly benign, policy-compliant task (e.g., translation, summarization, grammar polishing). Because the primary instruction is harmless, the LLM's safety filters…

Large Language Models (LLMs) are vulnerable to a jailbreak technique termed "Priority Hacking." Adversaries can bypass safety alignments by exploiting the model's internal priority graph, where certain abstract values (e.g., justice, public health) implicitly outweigh general safety restrictions within specific contexts. By crafting a deceptive prompt that frames a malicious request as a necessary action in service of a higher-priority benign value, attackers engineer a value conflict. The…

A prompt structure vulnerability exists in instruction-tuned Large Language Models (LLMs) where attackers can bypass safety alignments by injecting a continuation-triggering suffix immediately following the user prompt termination token. By placing an affirmative suffix outside the user instruction boundary, it is processed as the beginning of the assistant's own pre-filled response. This structural manipulation intrinsically overactivates the model's continuation attention heads, forcing its…

Embodied Large Language Models (LLMs) used for real-world agent planning are vulnerable to Action-level Manipulation (dubbed "Blindfold"), a jailbreak technique that bypasses semantic-level safety filters by exploiting the models' limited spatial and causal reasoning regarding physical consequences. Attackers can use an adversarial proxy LLM to decompose a semantically harmful intent into a sequence of individually benign primitive actions. To evade advanced semantic correlation checks…

Speech-driven Large Language Models (LLMs) and end-to-end Large Audio-Language Models (LALMs) are vulnerable to inaudible near-ultrasonic prompt injections, a framework dubbed Sirens' Whisper (SWhisper). By exploiting the non-linear response of commodity microphones, attackers can encode structured, phonetically optimized adversarial prompts into the 17–22 kHz near-ultrasonic band. Using regularized channel-inversion pre-compensation, the attacker shapes the waveform to account for microphone…

Multimodal Large Language Models (LLMs) are vulnerable to alignment bypass via Inter-Turn Modality Switching (ITMS). By systematically rotating the input modality (e.g., alternating between text, audio, and image) across successive turns in a multi-turn adversarial conversation, an attacker can destabilize the model's safety defenses. The cross-modal transition mechanism exploits alignment gaps between differing input processing pipelines, accelerating the erosion of safety guardrails and…

A vulnerability in multi-step, tool-using Large Language Model (LLM) agents allows attackers to bypass safety guardrails by manipulating user context variables, such as personalization profiles or persistent memory. The safety policies of frontier LLMs are highly context-dependent; inserting innocuous user bios (e.g., demographic or health disclosures) fundamentally alters the agent's action policy. When combined with lightweight adversarial jailbreaks, specific personalization contexts…

Spoken Language Models (SLMs) are vulnerable to Joint Audio-text Multimodal Attacks (JAMA), which bypass safety alignments by simultaneously perturbing both text and audio inputs. The vulnerability exploits the combined optimization of a discrete text suffix via Greedy Coordinate Gradient (GCG) and a continuous audio perturbation via Projected Gradient Descent (PGD). This joint gradient-based attack pushes the model's hidden layer representations into a distinct subspace far from the benign…

Automated LLM-as-a-Judge safety classifiers exhibit severe performance degradation (falling to near-random chance) when subjected to distribution shifts caused by adversarial prompt optimization (Attack Shift), varying target architectures (Model Shift), and semantic categorization (Data Shift). Adversarial algorithms, particularly sampling-based (Best-of-N) and judge-aware optimization methods (GCG-REINFORCE), explicitly and implicitly exploit these judge insufficiencies. Instead of eliciting…