arXiv subjects

Athula Balachandran

Publications and source records attributed to Athula Balachandran.

6 recordsLinked to original sources

arXiv2026

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering

Open-weight video diffusion models can generate photorealistic unsafe content, from violence to misinformation, yet existing defenses either require expensive safety fine-tuning that degrades general capability, or apply external filters that are trivially bypassed by adversarial prompts. We present REINS (REpresentation-space INference-time Safety steering), a training-free method that aligns video diffusion models at inference time by steering their internal representations toward safe generation. Our key finding is that safety-relevant structure is linearly encoded in the hidden-state activations of video diffusion transformers, and a single direction, discovered via Supervised PCA on binary safety labels, suffices to separate safe from unsafe generation trajectories. At inference, adding this direction to hidden states at an intermediate transformer layer redirects generation from harmful content to semantically related safe alternatives, with no weight updates, no concept enumeration, and negligible computational overhead. Through mechanistic analysis, we reveal that while safety information accumulates monotonically with transformer depth, steering effectiveness peaks at intermediate layers (~50% depth), exposing a fundamental tradeoff between information availability and downstream propagation capacity. We evaluate REINS across 9 video diffusion models, multiple parameter scales (1.3B-5B), and both text-to-video and image-to-video generation, to our knowledge, the broadest safety evaluation suite in the video generation literature.

cs.CV↗

arXiv2025

SAGA: Source Attribution of Generative AI Videos

The proliferation of generative AI has led to hyper-realistic synthetic videos, escalating misuse risks and outstripping binary real/fake detectors. We introduce SAGA (Source Attribution of Generative AI videos), the first comprehensive framework to address the urgent need for AI-generated video source attribution at a large scale. Unlike traditional detection, SAGA identifies the specific generative model used. It uniquely provides multi-granular attribution across five levels: authenticity, generation task (e.g., T2V/I2V), model version, development team, and the precise generator, offering far richer forensic insights. Our novel video transformer architecture, leveraging features from a robust vision foundation model, effectively captures spatio-temporal artifacts. Critically, we introduce a data-efficient pretrain-and-attribute strategy, enabling SAGA to achieve state-of-the-art attribution using only 0.5\% of source-labeled data per class, matching fully supervised performance. Furthermore, we propose Temporal Attention Signatures (T-Sigs), a novel interpretability method that visualizes learned temporal differences, offering the first explanation for why different video generators are distinguishable. Extensive experiments on public datasets, including cross-domain scenarios, demonstrate that SAGA sets a new benchmark for synthetic video provenance, providing crucial, interpretable insights for forensic and regulatory applications.

cs.CV↗

arXiv2025

TruthLens: Visual Grounding for Universal DeepFake Reasoning

Detecting DeepFakes has become a crucial research area as the widespread use of AI image generators enables the effortless creation of face-manipulated and fully synthetic content, while existing methods are often limited to binary classification (real vs. fake) and lack interpretability. To address these challenges, we propose TruthLens, a novel, unified, and highly generalizable framework that goes beyond traditional binary classification, providing detailed, textual reasoning for its predictions. Distinct from conventional methods, TruthLens performs MLLM grounding. TruthLens uses a task-driven representation integration strategy that unites global semantic context from a multimodal large language model (MLLM) with region-specific forensic cues through explicit cross-modal adaptation of a vision-only model. This enables nuanced, region-grounded reasoning for both face-manipulated and fully synthetic content, and supports fine-grained queries such as "Does the eyes/nose/mouth look real or fake?"- capabilities beyond pretrained MLLMs alone. Extensive experiments across diverse datasets demonstrate that TruthLens sets a new benchmark in both forensic interpretability and detection accuracy, generalizing to seen and unseen manipulations alike. By unifying high-level scene understanding with fine-grained region grounding, TruthLens delivers transparent DeepFake forensics, bridging a critical gap in the literature.

cs.CV↗

arXiv2024

Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content

Existing DeepFake detection techniques primarily focus on facial manipulations, such as face-swapping or lip-syncing. However, advancements in text-to-video (T2V) and image-to-video (I2V) generative models now allow fully AI-generated synthetic content and seamless background alterations, challenging face-centric detection methods and demanding more versatile approaches. To address this, we introduce the \underline{U}niversal \underline{N}etwork for \underline{I}dentifying \underline{T}ampered and synth\underline{E}tic videos (\texttt{UNITE}) model, which, unlike traditional detectors, captures full-frame manipulations. \texttt{UNITE} extends detection capabilities to scenarios without faces, non-human subjects, and complex background modifications. It leverages a transformer-based architecture that processes domain-agnostic features extracted from videos via the SigLIP-So400M foundation model. Given limited datasets encompassing both facial/background alterations and T2V/I2V content, we integrate task-irrelevant data alongside standard DeepFake datasets in training. We further mitigate the model's tendency to over-focus on faces by incorporating an attention-diversity (AD) loss, which promotes diverse spatial attention across video frames. Combining AD loss with cross-entropy improves detection performance across varied contexts. Comparative evaluations demonstrate that \texttt{UNITE} outperforms state-of-the-art detectors on datasets (in cross-data settings) featuring face/background manipulations and fully synthetic T2V/I2V videos, showcasing its adaptability and generalizable detection capabilities.

cs.CV↗

arXiv2024

Can DeepFake Speech be Reliably Detected?

Recent advances in text-to-speech (TTS) systems, particularly those with voice cloning capabilities, have made voice impersonation readily accessible, raising ethical and legal concerns due to potential misuse for malicious activities like misinformation campaigns and fraud. While synthetic speech detectors (SSDs) exist to combat this, they are vulnerable to ``test domain shift", exhibiting decreased performance when audio is altered through transcoding, playback, or background noise. This vulnerability is further exacerbated by deliberate manipulation of synthetic speech aimed at deceiving detectors. This work presents the first systematic study of such active malicious attacks against state-of-the-art open-source SSDs. White-box attacks, black-box attacks, and their transferability are studied from both attack effectiveness and stealthiness, using both hardcoded metrics and human ratings. The results highlight the urgent need for more robust detection methods in the face of evolving adversarial threats.

cs.SD↗

arXiv2012

CARE: Content Aware Redundancy Elimination for Disaster Communications on Damaged Networks

During a disaster scenario, situational awareness information, such as location, physical status and images of the surrounding area, is essential for minimizing loss of life, injury, and property damage. Today's handhelds make it easy for people to gather data from within the disaster area in many formats, including text, images and video. Studies show that the extreme anxiety induced by disasters causes humans to create a substantial amount of repetitive and redundant content. Transporting this content outside the disaster zone can be problematic when the network infrastructure is disrupted by the disaster. This paper presents the design of a novel architecture called CARE (Content-Aware Redundancy Elimination) for better utilizing network resources in disaster-affected regions. Motivated by measurement-driven insights on redundancy patterns found in real-world disaster area photos, we demonstrate that CARE can detect the semantic similarity between photos in the networking layer, thus reducing redundant transfers and improving buffer utilization. Using DTN simulations, we explore the boundaries of the usefulness of deploying CARE on a damaged network, and show that CARE can reduce packet delivery times and drops, and enables 20-40% more unique information to reach the rescue teams outside the disaster area than when CARE is not deployed.

cs.NI↗